© 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. 85216
    Prev
    Next
    INDEX
    Explanations

    East India Company | Day

    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
    ский
    0.72
    ம்
    0.70
    思
    0.59
    ص
    0.57
    ába
    0.54
    هش
    0.54
    вати
    0.54
    楚
    0.54
    ets
    0.53
    ет
    0.52
    POSITIVE LOGITS
    t
    0.85
     an
    0.73
    LE
    0.72
        
    0.64
    >
    0.64
    of
    0.62
    are
    0.62
     \
    0.61
    WARD
    0.61
    ка
    0.61
    Activations Density 0.001%

    No Known Activations