© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9121
    Prev
    Next
    INDEX
    Explanations

    language describing candidates, elections, and political parties.

    oai_token-act-pair · gemini-2.0-flash

    judicial/political candidates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     candidate
    -3.00
     Candidate
    -2.88
     candidates
    -2.84
    Candidate
    -2.72
    candidate
    -2.70
     Candidates
    -2.70
    Candidates
    -2.56
     CANDIDATE
    -2.52
    candidates
    -2.45
     candidat
    -2.20
    POSITIVE LOGITS
     Atherton
    0.50
    σιο
    0.46
    LError
    0.45
    [::-
    0.44
    ymce
    0.43
    agg
    0.42
    STOT
    0.42
    viewport
    0.42
    jerk
    0.41
     pelan
    0.41
    Activations Density 3.726%

    No Known Activations