© 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. 84572
    Prev
    Next
    INDEX
    Explanations

    mystery and hidden things

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ine
    1.21
    ə
    1.19
    ت
    1.18
    uan
    1.16
    (
    1.12
    ारा
    1.09
    ě
    1.09
    ೊ
    1.09
    تها
    1.08
    imeter
    1.07
    POSITIVE LOGITS
    o
    2.72
    a
    2.30
    i
    2.09
    ન
    1.92
    ي
    1.91
    e
    1.80
    n
    1.77
    ে
    1.71
    IN
    1.69
    н
    1.60
    Activations Density 0.001%

    No Known Activations