© 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. 40024
    Prev
    Next
    INDEX
    Explanations

    Interwar period

    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
    al
    0.72
    '
    0.70
    蜢
    0.67
    <0x80>
    0.66
     EA
    0.65
     i
    0.65
     API
    0.63
     AGM
    0.63
     AKA
    0.62
    烺
    0.62
    POSITIVE LOGITS
    ру
    0.77
    u
    0.73
     insuficiente
    0.70
    म
    0.68
    리
    0.66
     primjer
    0.65
     pantalla
    0.65
    ay
    0.64
    ER
    0.64
    OT
    0.64
    Activations Density 0.003%

    No Known Activations