© 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. 162776
    Prev
    Next
    INDEX
    Explanations

    Giuoco Piano

    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
    {
    1.33
     który
    1.27
    ট
    1.23
    {:
    1.20
     cały
    1.20
    AN
    1.17
     conhecida
    1.17
     deoarece
    1.17
    '=
    1.16
     préférable
    1.16
    POSITIVE LOGITS
    is
    1.43
    n
    1.31
    y
    1.29
    an
    1.27
     It
    1.27
     is
    1.23
    re
    1.23
    ir
    1.15
     The
    1.07
    are
    1.03
    Activations Density 0.000%

    No Known Activations