© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129015
    Prev
    Next
    INDEX
    Explanations

    polypropylene, PEEK, terephthalate

    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_6_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
    ა
    0.74
    ए
    0.73
    在
    0.72
    swürdig
    0.71
    ı
    0.70
    ا
    0.69
    ي
    0.69
    ඔ
    0.68
    opportunities
    0.68
    st
    0.67
    POSITIVE LOGITS
     for
    0.76
     by
    0.60
     at
    0.59
    가는
    0.59
     of
    0.59
     coerced
    0.58
     salvo
    0.57
    σία
    0.56
     with
    0.55
    اری
    0.55
    Activations Density 0.001%

    No Known Activations