© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41143
    Prev
    Next
    INDEX
    Explanations

    date of agreement or event

    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_22_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
    uteen
    0.45
    ￠
    0.43
     chí
    0.40
     demais
    0.40
     পাঁচটি
    0.40
    🌇
    0.39
     chihuahua
    0.39
    ㄚ
    0.39
    絃
    0.39
     WATTS
    0.38
    POSITIVE LOGITS
     pretentious
    0.42
    先
    0.41
     étendue
    0.41
     marché
    0.40
    پاک
    0.40
    Depuis
    0.40
    History
    0.40
    Grand
    0.39
    رداری
    0.39
    依頼
    0.38
    Activations Density 0.000%

    No Known Activations