© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33369
    Prev
    Next
    INDEX
    Explanations

    Sasanian Empire

    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_3_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
    c
    1.08
    l
    1.02
    v
    1.00
    et
    0.99
    at
    0.95
    that
    0.93
    h
    0.90
    S
    0.89
    ro
    0.89
    R
    0.81
    POSITIVE LOGITS
     отлич
    0.82
    ;
    0.77
     жиз
    0.74
     Ashford
    0.73
     расчета
    0.73
     перспек
    0.72
     решения
    0.72
     задания
    0.71
     подс
    0.71
     срав
    0.71
    Activations Density 0.004%

    No Known Activations