© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4394
    Prev
    Next
    INDEX
    Explanations

    code snippets and associated keywords like function, if, session, and jogador

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     المعيارى
    -0.72
     صوتيه
    -0.71
    RenderAtEndOf
    -0.65
     متعلقه
    -0.64
    DockStyle
    -0.56
    SharedCtor
    -0.56
    ArrowToggle
    -0.56
    ValueStyle
    -0.55
    :✨
    -0.55
    GEBURTSDATUM
    -0.55
    POSITIVE LOGITS
    Conclusão
    0.57
    ^*)
    0.54
    Garantía
    0.52
    Atentamente
    0.50
    Producción
    0.48
    Ubicación
    0.48
    Etiquetas
    0.47
    ]}{
    0.47
    Dicas
    0.47
    </tfoot>
    0.47
    Activations Density 0.616%

    No Known Activations