© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4203
    Prev
    Next
    INDEX
    Explanations

    words related to political and/or legal advocacy

    oai_token-act-pair · gemini-2.0-flash

    defending/advocating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     AssemblyCulture
    -0.82
    AutoScaleMode
    -0.69
     Paglinawan
    -0.66
     Aner
    -0.61
    ?
    -0.60
    ivid
    -0.60
    λισ
    -0.58
     Antara
    -0.58
    incontro
    -0.56
     Bioaccumulative
    -0.56
    POSITIVE LOGITS
    <bos>
    0.85
     advocating
    0.72
    autoconfigure
    0.61
     typelib
    0.59
     fordern
    0.58
     propose
    0.57
     proposing
    0.56
    endpush
    0.55
    Advoc
    0.55
    advoc
    0.54
    Activations Density 1.107%

    No Known Activations