© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142506
    Prev
    Next
    INDEX
    Explanations

    Are you asking a question

    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_12_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
    7
    0.65
    éric
    0.62
    或
    0.62
     Lukas
    0.61
    ै
    0.59
    森
    0.57
    »
    0.55
     Sevent
    0.54
     शताब्दी
    0.54
     تاني
    0.53
    POSITIVE LOGITS
    marriage
    0.52
    涜
    0.51
    itare
    0.49
    toare
    0.48
    ită
    0.48
    🛋
    0.47
     suc
    0.46
    uzione
    0.46
     carpeting
    0.46
     প্রশিক্ষণ
    0.45
    Activations Density 0.007%

    No Known Activations