© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11910
    Prev
    Next
    INDEX
    Explanations

    academic or technical writing containing numbers, symbols, and abbreviations, often in the context of scientific data or publications

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    MigrationBuilder
    -0.50
     '{@
    -0.48
    WithIOException
    -0.43
    kloped
    -0.40
    InjectAttribute
    -0.39
    MessageOf
    -0.36
    yntaxException
    -0.36
    Derbyniad
    -0.35
    NameInMap
    -0.35
    :✨
    -0.34
    POSITIVE LOGITS
     N
    0.58
     Z
    0.58
     H
    0.58
     JL
    0.57
    ZD
    0.56
    empêcher
    0.56
     Cot
    0.56
    WHM
    0.56
     G
    0.56
     KT
    0.56
    Activations Density 18.423%

    No Known Activations