© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11719
    Prev
    Next
    INDEX
    Explanations

    phrases indicating passive attribution

    oai_token-act-pair · gemini-2.0-flash

    Giving credit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     credit
    -2.97
     Credit
    -2.59
    credit
    -2.56
    Credit
    -2.45
     CREDIT
    -2.36
    CREDIT
    -2.02
     credits
    -1.91
     credited
    -1.89
     Credits
    -1.76
     crédit
    -1.71
    POSITIVE LOGITS
    expandindo
    0.79
    IntoConstraints
    0.75
    StructEnd
    0.71
    //~
    0.70
     виправивши
    0.69
    __":
    0.69
     esternos
    0.68
    帖最后由
    0.65
    principalColumn
    0.64
    ztály
    0.63
    Activations Density 1.814%

    No Known Activations