© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62699
    Prev
    Next
    INDEX
    Explanations

    TTRPG system

    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_2_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
    ك
    1.07
     א
    0.97
    ק
    0.95
    মূলক
    0.94
     be
    0.93
    D
    0.90
     have
    0.89
     aé
    0.87
     voll
    0.87
    ർ
    0.86
    POSITIVE LOGITS
    s
    1.32
    ی
    1.27
    ्स
    1.18
    ς
    1.08
    to
    1.02
    но
    1.00
    ੋ
    0.97
    нения
    0.96
    ਆਂ
    0.96
    ের
    0.96
    Activations Density 0.000%

    No Known Activations