© 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. 85244
    Prev
    Next
    INDEX
    Explanations

    Eur- prefix, European organizations, geopolitical events

    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
    ร
    0.76
    و
    0.72
    ل
    0.72
    ك
    0.72
    as
    0.70
    ین
    0.68
    az
    0.67
    น
    0.67
    .
    0.66
     as
    0.66
    POSITIVE LOGITS
    getSt
    0.61
    PT
    0.60
    frameN
    0.59
     lentes
    0.58
     Що
    0.58
    LV
    0.57
    Mm
    0.56
    MV
    0.55
     personnelles
    0.55
     hsize
    0.55
    Activations Density 0.000%

    No Known Activations