© 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. 24005
    Prev
    Next
    INDEX
    Explanations

    you questions and statements

    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
    ض
    0.90
    দ
    0.73
    不允许
    0.73
    جراء
    0.71
    بد
    0.68
    钨
    0.68
    បង្
    0.66
    މ
    0.66
    اد
    0.64
    。",
    0.64
    POSITIVE LOGITS
    al
    0.96
     de
    0.90
    ay
    0.88
    ai
    0.82
    ای
    0.78
    el
    0.77
     is
    0.76
    AL
    0.76
    alang
    0.75
    ında
    0.75
    Activations Density 0.046%

    No Known Activations