© 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. 121694
    Prev
    Next
    INDEX
    Explanations

    Steven Wright

    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
    سلم
    0.80
    ال
    0.76
    OCCO
    0.76
    ە
    0.75
    ຂໍ້ມ
    0.74
    ت
    0.74
    sweater
    0.72
    िडेट
    0.70
    IMI
    0.70
    เร็จ
    0.68
    POSITIVE LOGITS
    0.70
    o
    0.68
    를
    0.66
    S
    0.61
    oi
    0.59
     σκ
    0.56
    ↵↵
    0.56
    ua
    0.56
     ملاقات
    0.56
    N
    0.55
    Activations Density 0.008%

    No Known Activations