© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40771
    Prev
    Next
    INDEX
    Explanations

    optic nerve

    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_3_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
    ли
    0.76
    ग
    0.73
     फिल्मी
    0.71
    Solution
    0.71
    Produkt
    0.70
    다라고
    0.65
    高志森
    0.64
    Process
    0.64
    Park
    0.63
     VLAN
    0.63
    POSITIVE LOGITS
    ك
    1.07
    ка
    0.68
     optimizing
    0.65
     optimise
    0.64
     оптими
    0.64
     опти
    0.63
    с
    0.63
    ০০
    0.61
     óptica
    0.61
     beaten
    0.60
    Activations Density 0.001%

    No Known Activations