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-3-12B-IT
12-GEMMASCOPE-2-RES-16K
2300
Prev
Next
MODEL
12-gemmascope-2-res-16k
Source/SAE
INDEX
Go
Explanations
words and phrases indicating retrieved, collected, or processed information that has been provided or extracted.
oai_token-act-pair · claude-4-5-haiku
Triggered by @aditix
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
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-3-12b-it/12-gemmascope-2-res-16k/2300?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-3-12b-it/12-gemmascope-2-res-16k/2300?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
1.22
as
1.09
in
1.06
he
1.06
on
1.05
our
1.04
for
1.02
an
1.02
theatres
1.02
to
1.00
POSITIVE LOGITS
ار
1.24
và
1.09
ay
1.06
Freddy
1.05
أ
1.04
ᱨ
1.04
до
1.03
箖
1.03
的主要
1.02
addPreferredGap
1.00
Act
ivations
Density 0.239%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
