© 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. 226741
    Prev
    Next
    INDEX
    Explanations

    foreign language prefixes/suffixes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ى
    0.96
    지
    0.94
    I
    0.92
    راً
    0.87
    لا
    0.85
    도
    0.84
     I
    0.84
     carénés
    0.83
    ری
    0.82
    在
    0.82
    POSITIVE LOGITS
     de
    1.01
    ut
    0.95
     is
    0.95
    ap
    0.92
    '
    0.88
    ad
    0.87
    .
    0.84
    ana
    0.82
    d
    0.82
    a
    0.80
    Activations Density 0.000%

    No Known Activations