© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12560
    Prev
    Next
    INDEX
    Explanations

    names, particularly those of academics and professionals

    oai_token-act-pair · gemini-2.0-flash

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ReusableCell
    -0.71
    ka
    -0.57
    GIH
    -0.54
    MigrationBuilder
    -0.52
    Ayr
    -0.52
    KA
    -0.51
    کو
    -0.49
     للاسماء
    -0.48
    //
    -0.47
    asible
    -0.47
    POSITIVE LOGITS
    StoryboardSegue
    0.58
    extAlignment
    0.56
    ArrowToggle
    0.55
    Bildung
    0.53
    ViewFeatures
    0.52
    ThroughAttribute
    0.52
    tanleria
    0.51
     ImportError
    0.51
    ườ
    0.50
     doInBackground
    0.50
    Activations Density 0.876%

    No Known Activations