© 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. 106962
    Prev
    Next
    INDEX
    Explanations

    Machu Picchu, Benchmark

    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
    {
    1.73
    ع
    1.63
    ا
    1.53
    ক
    1.53
     you
    1.48
    та
    1.46
    ן
    1.46
    ম
    1.45
    ু
    1.44
    <0x80>
    1.40
    POSITIVE LOGITS
    util
    1.18
     ਅਤੇ
    1.16
    几
    1.03
     प्रतिशत
    1.02
    २
    1.00
    er
    0.95
    land
    0.94
    grid
    0.92
    point
    0.91
    lington
    0.91
    Activations Density 0.000%

    No Known Activations