© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84566
    Prev
    Next
    INDEX
    Explanations

    suffix -о

    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_0_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
    র
    1.31
    n
    1.30
    ੰ
    1.27
     to
    1.21
    н
    1.20
     outlay
    1.17
    AY
    1.13
    ER
    1.05
     Albania
    1.05
    ン
    1.05
    POSITIVE LOGITS
    。
    1.92
    א
    1.89
    다
    1.77
    자
    1.68
    نا
    1.63
    ا
    1.63
    ні
    1.59
    ق
    1.58
    ند
    1.54
    اي
    1.53
    Activations Density 0.000%

    No Known Activations