© 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. 11337
    Prev
    Next
    INDEX
    Explanations

    words related to management/production

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     Ressource
    -0.50
     typelib
    -0.50
     harte
    -0.50
     Мексичка
    -0.49
     ComVisible
    -0.47
    횟
    -0.47
    KommentareTeilen
    -0.47
    AddHtmlAttribute
    -0.45
     travaillons
    -0.44
    consulté
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.62
    SerializedSize
    0.58
    Rüyada
    0.58
    QMetaType
    0.58
    WriteLiteral
    0.57
     snippetHide
    0.57
    parsedMessage
    0.57
    legal
    0.56
    WEEN
    0.54
     legal
    0.54
    Activations Density 7.309%

    No Known Activations