© 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. 2549
    Prev
    Next
    INDEX
    Explanations

    code snippets, possibly Python, and related terms like "return", "def", variable names, array, and loops

    oai_token-act-pair · gemini-2.0-flash

    coding syntax in Python, particularly related to lists and arrays

    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
     ſeveral
    -0.75
     Monfieur
    -0.74
     disambiguazione
    -0.71
    DllImport
    -0.67
    RuleContext
    -0.67
     itſelf
    -0.66
     Efq
    -0.64
    ſelf
    -0.64
    GEBURTSDATUM
    -0.63
     iconFacebook
    -0.62
    POSITIVE LOGITS
     double
    0.58
     [
    0.56
    sprü
    0.47
    double
    0.46
     np
    0.45
    [
    0.44
    []
    0.41
    THRESH
    0.40
     []
    0.40
     (
    0.39
    Activations Density 6.128%

    No Known Activations