© 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. 129126
    Prev
    Next
    INDEX
    Explanations

    daylight hours

    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
    ন
    1.02
    a
    0.92
     funkci
    0.87
    只限平日
    0.87
    ย
    0.86
    o
    0.83
     chock
    0.82
    ન
    0.82
    на
    0.81
    oš
    0.81
    POSITIVE LOGITS
    O
    0.99
    cad
    0.88
    ע
    0.86
    ح
    0.86
    A
    0.84
    ים
    0.84
    bg
    0.83
    achat
    0.81
    Ⅰ
    0.80
    In
    0.80
    Activations Density 0.000%

    No Known Activations