© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135347
    Prev
    Next
    INDEX
    Explanations

    Knox

    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_6_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
    ٢
    1.01
    وي
    0.94
    ٥
    0.94
    وري
    0.93
    ﾞ
    0.93
     ايجاد
    0.91
    ố
    0.90
    cheidet
    0.89
    િંહ
    0.87
    ו
    0.87
    POSITIVE LOGITS
    t
    1.20
    เป็น
    1.15
    จะ
    1.02
    กับ
    0.99
    h
    0.98
    /
    0.97
     additives
    0.95
    -
    0.92
    ق
    0.89
    ב
    0.88
    Activations Density 0.000%

    No Known Activations