Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-3-4B-IT
31-GEMMASCOPE-2-TRANSCODER-262K
9319
Prev
Next
MODEL
31-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-2-4b-it/transcoder_all/layer_31_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-3-4b-it/31-gemmascope-2-transcoder-262k/9319?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-3-4b-it/31-gemmascope-2-transcoder-262k/9319?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
講的是
0.74
ening
0.72
curr
0.71
ta
0.71
Both
0.69
ened
0.68
Both
0.67
पुरस्कार
0.67
ത
0.66
उस
0.66
POSITIVE LOGITS
Ce
1.03
Ce
0.95
ce
0.90
ce
0.78
CE
0.77
cei
0.76
Care
0.75
care
0.67
மெ
0.65
qu
0.64
Act
ivations
Density 0.002%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
