© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12873
    Prev
    Next
    INDEX
    Explanations

    snippets of source code, especially in Java or Android

    oai_token-act-pair · gemini-2.0-flash

    coding constructs and functions in programming

    np_token-act-pair-logits · gpt-4o-mini

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ans
    -0.54
     ransomware
    -0.53
    cline
    -0.52
    Bearer
    -0.51
     bore
    -0.50
     hemel
    -0.49
     chèvre
    -0.48
     Wray
    -0.48
     Bearer
    -0.48
    Legenda
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.97
    IntoConstraints
    0.96
     مرئيه
    0.87
     Мексичка
    0.85
    djangoproject
    0.82
    MigrationBuilder
    0.78
     MainAxisSize
    0.75
     विश्वसनीयता
    0.75
     <=",
    0.75
     AttributeSet
    0.73
    Activations Density 1.137%

    No Known Activations