© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24905
    Prev
    Next
    INDEX
    Explanations

    Royal

    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_56_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
    皇
    0.45
     Royal
    0.45
     ROYAL
    0.42
    ROY
    0.40
     royal
    0.40
     Roy
    0.39
     royalty
    0.39
     Royale
    0.38
     royale
    0.38
     penalty
    0.37
    POSITIVE LOGITS
    Family
    1.16
     Family
    1.08
    族
    1.04
    족
    1.02
    FAMILY
    1.00
     FAMILY
    0.97
    family
    0.96
     family
    0.96
    族的
    0.88
    室
    0.83
    Activations Density 0.004%

    No Known Activations