© 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. 47350
    Prev
    Next
    INDEX
    Explanations

    disaster relief

    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
    ти
    0.89
    ка
    0.86
    O
    0.86
    U
    0.71
    I
    0.69
    H
    0.69
    تي
    0.67
    Y
    0.66
    E
    0.66
    做
    0.64
    POSITIVE LOGITS
    다
    0.69
    닙
    0.67
    ac
    0.65
     that
    0.62
    mec
    0.60
     as
    0.59
    ills
    0.58
     THAT
    0.58
     It
    0.57
     että
    0.57
    Activations Density 0.004%

    No Known Activations