© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 19095
    Prev
    Next
    INDEX
    Explanations

    I've

    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_34_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
     говорят
    0.38
     khảo
    0.38
    وات
    0.36
    ร่วม
    0.36
     pédicule
    0.35
     રૂપ
    0.35
     পাট
    0.35
    уы
    0.35
     mới
    0.34
    阶
    0.34
    POSITIVE LOGITS
     मदर
    0.39
    ికె
    0.36
     funk
    0.36
    ධ
    0.35
    stell
    0.35
     Display
    0.34
     Signal
    0.34
     Summar
    0.34
    ResponseMessage
    0.34
     summaries
    0.34
    Activations Density 0.083%

    No Known Activations