© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209485
    Prev
    Next
    INDEX
    Explanations

    ir, for exampleir, void, base, redir, void, base, red

    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_5_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
    to
    1.02
    '
    0.91
    ي
    0.90
    {
    0.88
    는
    0.87
    то
    0.87
    ра
    0.85
    ’
    0.79
    <0x80>
    0.76
    UR
    0.76
    POSITIVE LOGITS
     on
    0.91
    et
    0.76
     aisl
    0.73
     an
    0.72
    og
    0.70
     e
    0.70
     apresent
    0.68
     have
    0.66
     ample
    0.66
     estern
    0.64
    Activations Density 0.035%

    No Known Activations