© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2452
    Prev
    Next
    INDEX
    Explanations

    computer code-related tokens, especially tags and attributes in a structured data format like XML or a programming language.

    oai_token-act-pair · gemini-2.0-flash

    code, logs, statistics

    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
    MigrationBuilder
    -1.12
    writeFieldEnd
    -1.04
     AssemblyCulture
    -0.98
     JpaRepository
    -0.95
     ProtoMessage
    -0.92
     MyBatis
    -0.91
    Hochspringen
    -0.90
     ModelExpression
    -0.90
    Personendaten
    -0.89
    ValueStyle
    -0.88
    POSITIVE LOGITS
     blest
    0.56
    less
    0.47
     powdered
    0.46
     progeny
    0.46
     Indep
    0.45
     repression
    0.44
    parametri
    0.43
     lowland
    0.42
     datter
    0.42
     colouring
    0.41
    Activations Density 11.805%

    No Known Activations