© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 199146
    Prev
    Next
    INDEX
    Explanations

    superseded

    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_4_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
    కు
    0.13
    ﺖ
    0.13
    ﻛ
    0.12
     Счетчик
    0.12
    ﻪ
    0.11
    he
    0.11
     Система
    0.11
    ти
    0.11
    ﺭ
    0.11
    they
    0.11
    POSITIVE LOGITS
     to
    0.24
    리
    0.16
    re
    0.15
    )
    0.15
    ار
    0.15
     at
    0.15
    ED
    0.15
    de
    0.14
    ー
    0.14
    to
    0.14
    Activations Density 0.000%

    No Known Activations