© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 219070
    Prev
    Next
    INDEX
    Explanations

    god rays

    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_16_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
    。
    0.49
    兵
    0.47
    适应
    0.47
    ારીખ
    0.46
    ۔
    0.43
    uner
    0.43
    ｙ
    0.43
    虾
    0.42
    ia
    0.42
    ibir
    0.42
    POSITIVE LOGITS
     affect
    0.52
     booths
    0.52
     plough
    0.51
     sorts
    0.50
     iss
    0.49
     maize
    0.48
     Ono
    0.47
     pouring
    0.47
     muš
    0.46
     delusions
    0.46
    Activations Density 0.000%

    No Known Activations