© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206652
    Prev
    Next
    INDEX
    Explanations

    eye level

    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_37_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
     mirror
    0.47
    Mirror
    0.47
     mirrors
    0.44
    Surface
    0.41
     Mirror
    0.41
     figura
    0.41
    磨
    0.41
     reminding
    0.40
    鏡
    0.40
     reminders
    0.40
    POSITIVE LOGITS
     Eye
    0.53
     eye
    0.52
    Eye
    0.51
    eye
    0.48
     ईयर
    0.46
     EYE
    0.46
     Auge
    0.42
    눈
    0.41
     göz
    0.41
     virtual
    0.39
    Activations Density 0.002%

    No Known Activations