© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8110
    Prev
    Next
    INDEX
    Explanations

    substrings within numerical references to published papers, including the brackets, author codes, and year

    oai_token-act-pair · gemini-2.0-flash

    detecting years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Попис
    -0.42
    LookAnd
    -0.42
    MIME
    -0.41
     viață
    -0.40
     delas
    -0.39
    Ext
    -0.39
    off
    -0.39
     PropTypes
    -0.38
     off
    -0.37
     useEffect
    -0.37
    POSITIVE LOGITS
    رشف
    0.85
    FieldBuilder
    0.76
    SharedDtor
    0.75
    Enllaces
    0.73
    RenderAtEndOf
    0.73
    Rüyada
    0.70
    ValueStyle
    0.69
    PageContext
    0.65
     nahilalakip
    0.65
    StructEnd
    0.64
    Activations Density 1.449%

    No Known Activations