© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107015
    Prev
    Next
    INDEX
    Explanations

    Quizlet and quiz contexts

    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_2_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
    ש
    1.77
    ح
    1.43
    to
    1.39
    و
    1.38
    മ
    1.23
    f
    1.20
    c
    1.20
    na
    1.13
    ف
    1.13
    and
    1.12
    POSITIVE LOGITS
     de
    1.03
    ну
    1.02
    ти
    0.94
     inflicted
    0.91
    нков
    0.90
     codified
    0.89
     cinco
    0.89
    к
    0.88
     cinque
    0.87
    ة
    0.87
    Activations Density 0.001%

    No Known Activations