© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192363
    Prev
    Next
    INDEX
    Explanations

    beanbag toss/chair

    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_4_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
    at
    0.92
     (
    0.88
     Aging
    0.79
    ojen
    0.72
     Gifts
    0.70
    ed
    0.69
     Cliffs
    0.67
     I
    0.64
     Radiant
    0.64
    ian
    0.64
    POSITIVE LOGITS
    ר
    0.99
     отмети
    0.86
     tè
    0.84
    ス
    0.84
    лі
    0.80
    мо
    0.77
    ર
    0.77
    ني
    0.76
    ллер
    0.76
    да
    0.76
    Activations Density 0.000%

    No Known Activations