© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11676
    Prev
    Next
    INDEX
    Explanations

    phrases related to clicking UI elements

    oai_token-act-pair · gemini-2.0-flash

    Webpage UI interactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Click
    -1.14
     Click
    -1.02
     click
    -0.97
    click
    -0.97
    Press
    -0.86
     Press
    -0.82
     press
    -0.82
     clicks
    -0.81
     clicking
    -0.79
    press
    -0.77
    POSITIVE LOGITS
    verwijspagina
    0.68
    InitVars
    0.68
    ########.
    0.66
    躇
    0.65
    InjectAttribute
    0.63
    曖昧さ回避
    0.61
     TAMBIÉN
    0.60
     فريبيس
    0.59
    出版年
    0.58
    abestanden
    0.58
    Activations Density 1.075%

    No Known Activations