© 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. 84805
    Prev
    Next
    INDEX
    Explanations

    ominously, hilar contours, obliviously

    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
    Negative Logits
    on
    1.64
    '
    1.57
    as
    1.55
    fe
    1.52
    ن
    1.45
    p
    1.35
    ’
    1.32
    ra
    1.31
    are
    1.30
    to
    1.30
    POSITIVE LOGITS
    ק
    1.70
     شرطونه
    1.29
     merciless
    1.20
     проверки
    1.20
    д
    1.20
    }$;
    1.19
    تين
    1.19
    اتي
    1.19
    Z
    1.18
    Б
    1.17
    Activations Density 0.000%

    No Known Activations