© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113197
    Prev
    Next
    INDEX
    Explanations

    sundries or sundress

    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_2_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
    ח
    1.44
    ین
    1.27
     інші
    1.12
     ragazze
    1.09
     piatta
    1.06
     август
    1.06
     доступны
    1.01
    عی
    0.99
     raccol
    0.98
     competenze
    0.98
    POSITIVE LOGITS
    s
    2.09
    i
    1.79
    y
    1.56
    ي
    1.52
    b
    1.52
    n
    1.42
    m
    1.39
    c
    1.38
    J
    1.35
    V
    1.33
    Activations Density 0.000%

    No Known Activations