© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109359
    Prev
    Next
    INDEX
    Explanations

    French and Russian suffixes/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_1_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
    ل
    1.74
     to
    1.73
    '
    1.48
    ي
    1.38
     I
    1.30
     deu
    1.24
     by
    1.20
    ﺍ
    1.20
    【
    1.18
    Vý
    1.16
    POSITIVE LOGITS
    ings
    1.10
    annya
    1.04
    та
    1.03
    ulating
    1.01
    تی
    0.98
     kepada
    0.96
    c
    0.92
     特に
    0.91
    ider
    0.89
     यांची
    0.89
    Activations Density 0.000%

    No Known Activations