© 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. 1197
    Prev
    Next
    INDEX
    Explanations

    code snippets that declare the main function

    oai_token-act-pair · gemini-2.0-flash

    say "main"

    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
    +#+#
    -0.44
    popd
    -0.42
    相关文章
    -0.40
    PageModule
    -0.40
     متعلقه
    -0.39
    Rüyada
    -0.39
    ModelSerializer
    -0.38
    Cubit
    -0.37
     liberty
    -0.37
    ראות
    -0.37
    POSITIVE LOGITS
     main
    2.56
    main
    2.45
    Main
    2.11
     MAIN
    2.03
    MAIN
    2.00
     Main
    1.97
     głów
    1.72
     hlavní
    1.66
     primary
    1.66
     hoved
    1.63
    Activations Density 2.401%

    No Known Activations