© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170476
    Prev
    Next
    INDEX
    Explanations

    senses, World, discussed, fire, repair

    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_20_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
    ুদ্ধে
    0.17
    Lightbox
    0.17
    ллин
    0.17
     टन
    0.16
    ರಿಂದ
    0.16
     ಯೋಜನೆ
    0.16
    দ্দিন
    0.16
    計画
    0.16
    敵人
    0.16
    殯
    0.16
    POSITIVE LOGITS
     an
    0.21
     a
    0.19
     as
    0.19
     with
    0.19
    ine
    0.18
     uma
    0.18
     tanto
    0.18
     along
    0.18
     aquele
    0.18
     aquela
    0.17
    Activations Density 0.000%

    No Known Activations