© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5134
    Prev
    Next
    INDEX
    Explanations

    words and symbols used to describe user interfaces and context menus, especially those related to right-clicking and touch screen actions.

    oai_token-act-pair · gemini-2.0-flash

    Clicking actions

    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
    document
    -0.79
     document
    -0.60
    ocument
    -0.55
    cline
    -0.52
    DOCUMENT
    -0.52
    OwnProperty
    -0.47
    doctype
    -0.47
    Document
    -0.45
     DOCUMENT
    -0.45
    doc
    -0.45
    POSITIVE LOGITS
     double
    0.90
     click
    0.86
    DOUBLE
    0.80
     DOUBLE
    0.77
     Double
    0.77
    Double
    0.74
    double
    0.74
     Click
    0.73
     clicks
    0.73
     long
    0.73
    Activations Density 1.024%

    No Known Activations