© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194814
    Prev
    Next
    INDEX
    Explanations

    ko

    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_50_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
    燔
    0.52
    CAL
    0.43
     Pember
    0.41
     Peyton
    0.40
    Capp
    0.38
    ᓇ
    0.38
    唐
    0.37
    Luc
    0.37
    Cal
    0.36
    Painter
    0.36
    POSITIVE LOGITS
     ко
    1.21
     ko
    1.19
     کو
    1.16
     কো
    1.10
     코
    1.09
     Ko
    1.00
    کو
    0.99
     ку
    0.98
     كو
    0.96
     KO
    0.93
    Activations Density 0.001%

    No Known Activations