© 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. 6933
    Prev
    Next
    INDEX
    Explanations

    mentions of countries, especially African and Middle Eastern countries, in the context of conflict or Javascript Object Notation (JSON)

    oai_token-act-pair · gemini-2.0-flash

    non-standard or unusual token patterns

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

    Countries

    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
    AutoScale
    -0.74
    webElementXpaths
    -0.64
     ExecuteAsync
    -0.61
    脚注の使い方
    -0.61
     initComponents
    -0.56
    ReadLine
    -0.56
    readString
    -0.56
    XmlEnum
    -0.55
     uska
    -0.55
     ویکی‌پدی
    -0.55
    POSITIVE LOGITS
     Photocase
    0.52
     tann
    0.47
     tannins
    0.46
    gab
    0.45
    GraphicsUnit
    0.43
    拳
    0.43
    Curi
    0.43
     ‪
    0.43
     Reunion
    0.42
    <u>
    0.42
    Activations Density 3.184%

    No Known Activations