© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10184
    Prev
    Next
    INDEX
    Explanations

    semicolons in C# code

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    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
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.69
    SystemColors
    -0.52
    RegressionTest
    -0.50
    DatabaseError
    -0.47
    hláš
    -0.46
     nahilalakip
    -0.46
     bere
    -0.46
     Drapeau
    -0.45
     unknownFields
    -0.45
     VIAF
    -0.45
    POSITIVE LOGITS
    zbęd
    0.68
     chré
    0.61
     sauvages
    0.59
     avoient
    0.57
     essentiels
    0.56
     Nacionales
    0.56
     tromper
    0.56
     domestiques
    0.56
     Imported
    0.55
     enfans
    0.55
    Activations Density 0.082%

    No Known Activations