© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12745
    Prev
    Next
    INDEX
    Explanations

    code related to Android apps

    oai_token-act-pair · gemini-2.0-flash

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     autorytatywna
    -1.08
     cherchés
    -0.96
    <bos>
    -0.95
    Autoritní
    -0.93
    TintMode
    -0.90
    PreferredItem
    -0.84
    oredCriteria
    -0.83
    transQ
    -0.83
    ьаж
    -0.81
    AsUp
    -0.81
    POSITIVE LOGITS
    runApp
    0.57
    ynb
    0.56
    HasForeignKey
    0.54
     RoutedEventArgs
    0.53
    springframework
    0.53
     CURLOPT
    0.53
    bli
    0.52
    Архівовано
    0.52
     irmãos
    0.52
     savez
    0.51
    Activations Density 1.196%

    No Known Activations