© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12530
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to layout and styling

    oai_token-act-pair · gemini-2.0-flash

    Code and layout

    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
     Roskov
    -1.25
    RenderAtEndOf
    -1.05
    RegistryLite
    -0.98
     дописавши
    -0.97
    migrationBuilder
    -0.96
    TagMode
    -0.95
     autorytatywna
    -0.94
     ExecuteAsync
    -0.93
    IVEREF
    -0.91
    SequentialGroup
    -0.90
    POSITIVE LOGITS
    auto
    0.44
     on
    0.39
    On
    0.36
    M
    0.35
    ip
    0.35
    on
    0.34
    in
    0.34
    //
    0.34
    is
    0.34
    ura
    0.33
    Activations Density 0.458%

    No Known Activations