Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
uzaymacar
/
gemma-3-27b-saes
like
1
Transformers
sparse_autoencoder
interpretability
sparse-autoencoder
sae
mechanistic-interpretability
dictionary-learning
gemma
arxiv:
2406.04093
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
gemma-3-27b-saes
/
layer_45
Commit History
Upload folder using huggingface_hub
cf0614b
verified
uzaymacar
commited on
Nov 24, 2025