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
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-3-4B-IT
25-GEMMASCOPE-2-TRANSCODER-262K
8632
Prev
Next
MODEL
25-gemmascope-2-transcoder-262k
Source/SAE
INDEX
Go
Explanations
i and j
np_max-act-logits · gemini-2.5-flash-lite
No Scores
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_25_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/25-gemmascope-2-transcoder-262k/8632?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/25-gemmascope-2-transcoder-262k/8632?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
ទទ
0.67
தக்க
0.65
ще
0.63
adt
0.62
ర్ప
0.62
邯
0.61
aryan
0.61
olischen
0.60
ouml
0.60
']))->
0.59
POSITIVE LOGITS
i
3.30
j
2.54
i
2.25
j
2.04
ii
1.98
ij
1.85
ｊ
1.77
ｉ
1.69
ij
1.62
ith
1.62
Act
ivations
Density 0.278%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
