© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3537
    Prev
    Next
    INDEX
    Explanations

    code snippets in a variety of languages, especially related to imports, classes, and function definitions in Java and Android

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    HtmlAttribute
    -0.85
    GEBURTSDATUM
    -0.69
    DebuggerNonUser
    -0.67
    migrationBuilder
    -0.66
    tagHelper
    -0.65
    sizeCache
    -0.65
    الدراسه
    -0.63
    TypedDataSet
    -0.63
    webElement
    -0.61
    onViewCreated
    -0.61
    POSITIVE LOGITS
     lệ
    0.50
     
    0.49
     Wex
    0.49
    ohjel
    0.48
     mukana
    0.48
     חיצוניים
    0.48
     bardak
    0.47
    base
    0.47
     detection
    0.47
     Kais
    0.47
    Activations Density 0.287%

    No Known Activations