© 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. 14917
    Prev
    Next
    INDEX
    Explanations

    proper names for people and companies

    oai_token-act-pair · gemini-2.0-flash

    names

    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
     mergeFrom
    -0.63
    WebElementEntity
    -0.62
    LookAnd
    -0.60
    DockStyle
    -0.59
     AssemblyCulture
    -0.57
    oneofs
    -0.56
     autorytatywna
    -0.54
     ModelExpression
    -0.54
    gameserver
    -0.53
    ngdoc
    -0.50
    POSITIVE LOGITS
    twimg
    0.61
    навли
    0.60
    ArgsConstructor
    0.58
    Pictured
    0.57
    Архівовано
    0.53
    excl
    0.52
     excluded
    0.52
    mereka
    0.51
     therewith
    0.51
    zustellen
    0.49
    Activations Density 0.685%

    No Known Activations