© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129026
    Prev
    Next
    INDEX
    Explanations

    theatre or opera house

    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_1_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
     ס
    1.10
     difficultés
    0.96
     dommages
    0.96
     מ
    0.95
     vías
    0.95
    스를
    0.94
     whistles
    0.93
     prácticas
    0.92
     vagas
    0.91
     δύο
    0.91
    POSITIVE LOGITS
    f
    1.34
    na
    1.29
    ta
    1.17
    ur
    1.14
    p
    1.10
    ut
    1.09
    it
    1.08
    ra
    1.08
    at
    1.07
    ang
    1.04
    Activations Density 0.000%

    No Known Activations