© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6048
    Prev
    Next
    INDEX
    Explanations

    interaction with user interfaces, particularly clicking actions

    oai_token-act-pair · gemini-2.0-flash

    clicking/selecting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     فريبيس
    -0.75
    writeField
    -0.61
    脚注の使い方
    -0.60
    ViewImports
    -0.60
    醐
    -0.57
    الحياه
    -0.57
    %</
    -0.56
    PreferredItem
    -0.55
    ()',
    -0.54
     ]
    -0.54
    POSITIVE LOGITS
     click
    1.23
     clicked
    1.05
     clicks
    1.05
     Click
    1.02
     clicking
    1.02
    CLICK
    1.02
    Click
    1.00
    click
    0.98
     CLICK
    0.97
     press
    0.96
    Activations Density 0.691%

    No Known Activations