© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9277
    Prev
    Next
    INDEX
    Explanations

    code snippets - finds assignment, conditionals, returns, parameters, and array-access

    oai_token-act-pair · gemini-2.0-flash

    PHP code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     فريبيس
    -0.79
     initComponents
    -0.79
     ujednoznacz
    -0.70
    SourceChecksum
    -0.65
    featureID
    -0.65
     esternos
    -0.65
    LookAnd
    -0.64
    ViewImports
    -0.62
    StoryboardSegue
    -0.62
     nahilalakip
    -0.60
    POSITIVE LOGITS
    
    0.57
     Arhivirano
    0.51
    didSet
    0.50
    ắc
    0.50
    echo
    0.49
     CURIAM
    0.49
    السكان
    0.49
     <>",
    0.48
    foreach
    0.48
    if
    0.48
    Activations Density 0.676%

    No Known Activations