© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78245
    Prev
    Next
    INDEX
    Explanations

    biographical information, research, and drama

    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_0_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
    k
    2.06
     for
    1.68
    kbar
    1.15
    𝟎
    1.14
    vés
    1.10
    kys
    1.10
    ك
    1.10
    kowej
    1.09
    س
    1.09
    ائي
    1.08
    POSITIVE LOGITS
    е
    1.89
    ۲
    1.88
    2
    1.86
    а
    1.63
    3
    1.61
    ﺭ
    1.59
    и
    1.52
    ă
    1.48
    の
    1.48
    อ
    1.46
    Activations Density 0.000%

    No Known Activations