© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8521
    Prev
    Next
    INDEX
    Explanations

    citations, especially of scientific papers

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.79
    te
    -0.50
    Хьажоргаш
    -0.45
     fine
    -0.44
     hyper
    -0.44
     offen
    -0.43
    FieldNumber
    -0.42
    ir
    -0.41
     off
    -0.41
     then
    -0.41
    POSITIVE LOGITS
    TagMode
    0.69
    principalTable
    0.67
    Datuak
    0.66
    AndEndTag
    0.66
     للمعارف
    0.62
    tonode
    0.61
    GHIJKLM
    0.56
    BagLayout
    0.55
    ⓧ
    0.54
     ModelExpression
    0.53
    Activations Density 0.229%

    No Known Activations