© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219497
    Prev
    Next
    INDEX
    Explanations

    medical

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     গুণে
    0.43
    γον
    0.42
     ans
    0.39
     eben
    0.37
    SpringMVCProject
    0.37
     चाँद
    0.37
     xung
    0.37
    諳
    0.37
     Fransiya
    0.36
    Jo
    0.36
    POSITIVE LOGITS
     medical
    0.48
     MEDICAL
    0.46
    medical
    0.44
     aute
    0.43
     médical
    0.43
     의료
    0.41
     Medical
    0.41
     मेडिकल
    0.41
    Medical
    0.40
     Osborn
    0.40
    Activations Density 0.007%

    No Known Activations