© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39837
    Prev
    Next
    INDEX
    Explanations

    foreign language fragments

    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_3_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
    y
    0.79
    ,
    0.76
    ן
    0.72
    ight
    0.71
    t
    0.68
    ،
    0.67
    ib
    0.64
     I
    0.64
    ows
    0.64
    rowave
    0.63
    POSITIVE LOGITS
    ור
    1.07
    د
    1.01
    ان
    0.90
    ל
    0.87
    ন
    0.86
    ת
    0.84
    其他
    0.84
    น
    0.83
    い
    0.80
    ని
    0.79
    Activations Density 0.003%

    No Known Activations