© 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. 140080
    Prev
    Next
    INDEX
    Explanations

    panels

    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
     Vehicles
    0.52
    vehicle
    0.50
     vehicle
    0.50
     veículos
    0.49
    Veh
    0.48
     VEH
    0.47
     Vehicle
    0.46
     vehicles
    0.46
     vehículos
    0.46
    乗
    0.46
    POSITIVE LOGITS
     panels
    0.89
    panels
    0.77
     Panels
    0.76
     пане
    0.75
     paneles
    0.74
     panel
    0.72
    パネル
    0.72
     Panel
    0.70
    Panel
    0.69
     панели
    0.66
    Activations Density 0.001%

    No Known Activations