© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3930
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to influencing people, asking for help from people, permission, community, leadership, strategy, impact, and measurable outcomes

    oai_token-act-pair · gemini-2.0-flash

    words indicating permission and authority

    np_token-act-pair-logits · gpt-4o-mini

    input, feedback

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    脚注の使い方
    -0.73
     MainAxisSize
    -0.68
     kaynağından
    -0.63
    abestanden
    -0.62
     recie
    -0.60
    aarrggbb
    -0.59
     initComponents
    -0.57
    GIVEREF
    -0.57
    uccio
    -0.57
     виправивши
    -0.57
    POSITIVE LOGITS
     from
    0.67
    <bos>
    0.50
     therefrom
    0.49
     ролях
    0.48
    市镇
    0.48
     bet
    0.47
     out
    0.46
     R
    0.46
     dintr
    0.46
     từ
    0.46
    Activations Density 16.975%

    No Known Activations