© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57469
    Prev
    Next
    INDEX
    Explanations

    facial treatments

    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_59_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
     facial
    1.27
     Facial
    1.13
    facial
    0.85
     얼굴
    0.60
    臉
    0.60
    脸
    0.56
     Face
    0.52
     face
    0.52
     wajah
    0.52
    顔
    0.50
    POSITIVE LOGITS
     fac
    1.41
    Fac
    1.27
    fac
    1.09
     Fac
    0.98
    FAC
    0.95
     FAC
    0.91
     Facilit
    0.61
     تسه
    0.55
     facilitators
    0.54
    facilit
    0.53
    Activations Density 0.002%

    No Known Activations