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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11530
    Prev
    Next
    INDEX
    Explanations

    words related to voting, challenges, fund-raising, contests, and marketing.

    oai_token-act-pair · gemini-2.0-flash

    polls and contests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Roskov
    -0.88
    __(/*!
    -0.81
     kasarigan
    -0.81
     contextLoads
    -0.77
     Ży
    -0.74
     Comprometido
    -0.72
     geho
    -0.72
    insics
    -0.69
    quelize
    -0.68
     оригіналу
    -0.68
    POSITIVE LOGITS
    <bos>
    0.91
    '
    0.51
     eventdata
    0.46
     actionTypes
    0.44
     market
    0.44
    se
    0.43
    ↵
    0.42
    店の
    0.42
    .
    0.42
    !
    0.41
    Activations Density 1.430%

    No Known Activations