© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10697
    Prev
    Next
    INDEX
    Explanations

    terms related to Indian government, business, and economics

    oai_token-act-pair · gemini-2.0-flash

    text containing organizations or government entities

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

    Government and industrial organization

    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
    addCriterion
    -0.73
     defaultstate
    -0.68
     singleton
    -0.63
    StoryboardSegue
    -0.57
     Trouver
    -0.57
     quæ
    -0.57
     chrétienne
    -0.52
     Saras
    -0.52
     Moderate
    -0.52
     thereon
    -0.51
    POSITIVE LOGITS
    rrggbb
    0.60
     ویکی‌پدیای
    0.55
    oa̍t
    0.50
    WriteBarrier
    0.49
    msford
    0.48
     出版
    0.47
     Sla
    0.46
    jenih
    0.46
    Tracce
    0.45
    Sla
    0.45
    Activations Density 0.661%

    No Known Activations