© 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. 162813
    Prev
    Next
    INDEX
    Explanations

    Sussex, Utrecht, Exeter

    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
    1.30
    ف
    1.16
    ка
    1.02
    ار
    1.02
    ات
    0.99
    اد
    0.98
    О
    0.96
    Observation
    0.96
    ierten
    0.94
    na
    0.91
    POSITIVE LOGITS
    お手
    0.90
    お届け
    0.82
     แม
    0.75
    㸵
    0.75
     saraf
    0.74
    ไม่ใช่
    0.74
     레이
    0.73
     لاکھ
    0.73
    お知らせ
    0.73
    おしゃれ
    0.72
    Activations Density 0.000%

    No Known Activations