© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12367
    Prev
    Next
    INDEX
    Explanations

    math and physics terminology, especially in the context of equations and analysis.

    oai_token-act-pair · gemini-2.0-flash

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     jadx
    -0.79
    Pautan
    -0.77
    GEBURTSDATUM
    -0.65
     فريبيس
    -0.63
    QtCore
    -0.62
    %";
    -0.61
    &_
    -0.61
    %",
    -0.61
    BeginInit
    -0.60
     &_
    -0.60
    POSITIVE LOGITS
    migrationBuilder
    0.56
     numerator
    0.54
     withdrawals
    0.51
     copii
    0.50
    ContentAlignment
    0.49
     withdraws
    0.49
    хара
    0.48
     cramp
    0.48
     Literatura
    0.48
     numberOfRows
    0.48
    Activations Density 2.644%

    No Known Activations