© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13199
    Prev
    Next
    INDEX
    Explanations

    eye exams and vision care

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     отправ
    0.42
     chemistry
    0.41
    Align
    0.38
    細
    0.36
    Sending
    0.36
    iern
    0.36
     sending
    0.36
    Chemistry
    0.35
     Chemistry
    0.34
     photographer
    0.34
    POSITIVE LOGITS
     eye
    0.72
     Eye
    0.72
    Eye
    0.67
     EYE
    0.66
    eye
    0.58
    眼
    0.57
     眼
    0.55
     eyew
    0.54
     глаза
    0.50
     exams
    0.49
    Activations Density 0.039%

    No Known Activations