© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30491
    Prev
    Next
    INDEX
    Explanations

    cozy and comforting words

    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_10_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
    ﺒ
    1.01
    گ
    0.97
    ای
    0.95
    ду
    0.84
    of
    0.83
    ۲
    0.83
    ﺮ
    0.83
    リン
    0.82
    ᱒
    0.82
    프
    0.82
    POSITIVE LOGITS
    us
    0.80
    uwa
    0.73
    leme
    0.72
     wreath
    0.71
    يي
    0.70
    arend
    0.69
    ığı
    0.68
    iation
    0.67
     পরি
    0.66
    ği
    0.66
    Activations Density 0.002%

    No Known Activations