© 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. 40046
    Prev
    Next
    INDEX
    Explanations

    physical examination and health systems

    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
    Negative Logits
    є
    0.69
    ي
    0.66
    จะ
    0.63
    i
    0.61
     хочется
    0.60
    is
    0.58
     גדול
    0.58
    는
    0.57
    是
    0.56
    য়া
    0.55
    POSITIVE LOGITS
    nél
    0.80
    मंडल
    0.79
    nál
    0.77
    slag
    0.76
    germ
    0.75
    norm
    0.73
    nemen
    0.73
    пу
    0.71
    réal
    0.71
    B
    0.70
    Activations Density 0.016%

    No Known Activations