© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40895
    Prev
    Next
    INDEX
    Explanations

    d/dx or d/dt derivatives

    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
     Испа
    0.77
    د
    0.75
     플레이
    0.70
    विद्यालय
    0.69
     Shyam
    0.68
    ptăm
    0.67
     Вул
    0.67
    ブラ
    0.66
    drawing
    0.66
    ानगर
    0.66
    POSITIVE LOGITS
    0.83
    o
    0.69
     weniger
    0.63
    </
    0.61
     functioned
    0.60
     by
    0.57
    ő
    0.56
     nacht
    0.55
     finalized
    0.54
     instigated
    0.54
    Activations Density 0.012%

    No Known Activations