© 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. 135420
    Prev
    Next
    INDEX
    Explanations

    shorter

    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
    :
    1.13
    al
    0.87
    ið
    0.85
    ลก
    0.81
    at
    0.79
     shamb
    0.78
    i
    0.77
    u
    0.77
     minimo
    0.75
     ऑफ
    0.75
    POSITIVE LOGITS
    ف
    1.12
     you
    1.09
    اری
    1.04
    ه‌ها
    0.98
    大
    0.98
    ان
    0.96
    وری
    0.92
    arı
    0.91
     You
    0.90
    נו
    0.89
    Activations Density 0.001%

    No Known Activations