© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77075
    Prev
    Next
    INDEX
    Explanations

    "ku" or "ker"

    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_53_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
     Wyd
    0.45
     тро
    0.44
    OPA
    0.44
     TRO
    0.40
    тро
    0.40
    TRO
    0.40
     tro
    0.39
     Wab
    0.39
     ప్రా
    0.38
    팜
    0.38
    POSITIVE LOGITS
     ku
    0.58
     Ku
    0.58
    Ku
    0.57
     ker
    0.49
     Ker
    0.47
     pu
    0.46
     quantity
    0.45
    Ker
    0.43
    ouer
    0.43
    ku
    0.41
    Activations Density 0.001%

    No Known Activations