© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102877
    Prev
    Next
    INDEX
    Explanations

    database partitioning and sharding strategy

    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_14_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
    ח
    0.63
     Prend
    0.57
     dems
    0.55
    discard
    0.55
    uanya
    0.54
    বর
    0.54
     deri
    0.54
    σο
    0.53
    ;
    0.53
    sau
    0.52
    POSITIVE LOGITS
    地图
    0.62
    igma
    0.54
    邻
    0.54
    浏览器
    0.52
     通常
    0.51
    িমুখে
    0.51
     න
    0.50
     ის
    0.50
     unhappiness
    0.49
    <0xAB>
    0.48
    Activations Density 0.000%

    No Known Activations