© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3862
    Prev
    Next
    INDEX
    Explanations

    steps in instructions, especially involving clicking or choosing options

    oai_token-act-pair · gemini-2.0-flash

    choose

    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
    Negative Logits
     click
    -1.20
     clicking
    -1.06
     press
    -1.02
     clicks
    -1.02
    click
    -1.00
     clicked
    -0.98
     presses
    -0.97
     pressed
    -0.97
     Press
    -0.95
     klik
    -0.95
    POSITIVE LOGITS
    出版年
    0.73
     فريبيس
    0.62
    ViewImports
    0.57
    脚注の使い方
    0.56
    writeField
    0.54
    ﴿
    0.54
    WebElementEntity
    0.52
    ]")]
    0.52
    ELF
    0.51
     Tenga
    0.51
    Activations Density 0.748%

    No Known Activations