© 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. 226591
    Prev
    Next
    INDEX
    Explanations

    time and its nature

    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
    데
    1.13
     provoqu
    1.10
    ного
    1.05
    ți
    1.05
    де
    0.96
    이면
    0.95
    지
    0.93
    ジ
    0.93
    지에
    0.92
    ם
    0.92
    POSITIVE LOGITS
     an
    1.20
     T
    1.09
    et
    1.00
     I
    0.95
     N
    0.94
    t
    0.91
    ella
    0.91
     R
    0.90
    ral
    0.90
     eller
    0.88
    Activations Density 0.009%

    No Known Activations