© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8650
    Prev
    Next
    INDEX
    Explanations

    psychiatrist, medication, drug

    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_13_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
     площа
    0.50
     dịch
    0.48
    િયન
    0.47
    residential
    0.47
    तरी
    0.46
     দূতাব
    0.46
     electrician
    0.45
     سوش
    0.45
     الخدم
    0.45
    洌
    0.45
    POSITIVE LOGITS
     medication
    0.54
     médicaments
    0.54
     médicament
    0.52
    𝐓
    0.49
     medicines
    0.48
     well
    0.48
     medications
    0.48
     Drug
    0.47
     Tuberculosis
    0.47
    药
    0.47
    Activations Density 0.042%

    No Known Activations