© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 214922
    Prev
    Next
    INDEX
    Explanations

    lunch time intervals

    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_31_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
     विधे
    0.39
    信息的
    0.39
     লিখিত
    0.38
     resented
    0.37
     Struct
    0.36
    状况
    0.34
    unning
    0.34
    enumerate
    0.33
    咂
    0.33
    print
    0.33
    POSITIVE LOGITS
     വ്യാപ
    0.46
     தஞ்ச
    0.43
    getLocation
    0.39
     nearby
    0.39
    ရောက်
    0.37
     هسه
    0.36
     déjeuner
    0.36
     الرياضيات
    0.36
     località
    0.36
    िक्ष
    0.36
    Activations Density 0.004%

    No Known Activations