© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Gemma-3-27B-IT
57-GEMMASCOPE-2-TRANSCODER-262K
228719
Prev
Next
MODEL
57-gemmascope-2-transcoder-262k
Source/SAE
INDEX
Go
Explanations
No Explanations Found
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-27b-it/transcoder_all/layer_57_width_262k_l0_small_affine
How To Load
Prompts (Dashboard)
238,145 prompts, 512 tokens each
Dataset (Dashboard)
lmsys + oasst1
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-3-27b-it/57-gemmascope-2-transcoder-262k/228719?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-3-27b-it/57-gemmascope-2-transcoder-262k/228719?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
j
0.42
sous
0.42
bxa
0.40
pro
0.39
towel
0.39
詛
0.39
வல
0.39
剌
0.39
tilted
0.38
최
0.38
POSITIVE LOGITS
pou
0.86
Pou
0.60
Pou
0.54
pou
0.48
uv
0.47
uv
0.43
já
0.39
tím
0.39
proud
0.38
brat
0.38
Act
ivations
Density 0.000%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
