© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9221
    Prev
    Next
    INDEX
    Explanations

    instances of clicking elements or images

    oai_token-act-pair · gemini-2.0-flash

    Clicking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     clicked
    -1.15
     clicks
    -1.10
     clicking
    -1.07
     click
    -1.07
     Click
    -1.03
    click
    -0.93
    Click
    -0.91
    clicks
    -0.90
     CLICK
    -0.87
    clicking
    -0.85
    POSITIVE LOGITS
    BeginContext
    0.51
    ModelSerializer
    0.51
    Sklici
    0.46
     gezet
    0.45
     Bodies
    0.45
    guest
    0.44
    viewWillAppear
    0.43
    CreateModel
    0.41
     ComVisible
    0.41
     disposizione
    0.41
    Activations Density 5.288%

    No Known Activations