© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34530
    Prev
    Next
    INDEX
    Explanations

    market discipline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0x0D>
    0.72
     hydrolyzed
    0.66
     мод
    0.62
    for
    0.61
    arı
    0.61
    ana
    0.59
     for
    0.58
     видео
    0.57
    -
    0.56
    were
    0.56
    POSITIVE LOGITS
    ض
    0.75
    ק
    0.70
    ق
    0.69
    시장
    0.66
    ח
    0.66
    جس
    0.65
    ك
    0.64
    วน
    0.60
    Markets
    0.60
    셨
    0.59
    Activations Density 0.003%

    No Known Activations