© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    code-related keywords (often found in programming languages)

    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
     docking
    -0.41
    ixote
    -0.38
     Front
    -0.37
     bras
    -0.37
    untamente
    -0.37
    話題
    -0.37
     bus
    -0.37
    altor
    -0.36
     Board
    -0.36
    Notation
    -0.35
    POSITIVE LOGITS
    SerializedSize
    0.92
    sizeCache
    0.91
    PreferredItem
    0.83
    IsMutable
    0.81
    tagHelperRunner
    0.80
     <=",
    0.79
    AutoScale
    0.77
    Tembelea
    0.77
    RTEE
    0.75
    parsedMessage
    0.73
    Activations Density 10.586%

    No Known Activations