© 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. 197836
    Prev
    Next
    INDEX
    Explanations

    speech acts and conversational maxims

    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
    iveness
    0.54
    ٹس
    0.54
     lɛ
    0.51
    ('')
    0.50
     onshore
    0.50
    빙
    0.49
     dryness
    0.49
    の水
    0.48
     antifreeze
    0.48
     esiste
    0.48
    POSITIVE LOGITS
     গর্ব
    0.54
     शो
    0.53
    اديم
    0.53
     정말
    0.52
     ஆதார
    0.50
    ettes
    0.50
     काउंसलिंग
    0.50
     मेडिकल
    0.47
     World
    0.47
    殼
    0.46
    Activations Density 0.001%

    No Known Activations