© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126376
    Prev
    Next
    INDEX
    Explanations

    New York, Yorkshire, Yorkville, york

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ur
    0.73
    urado
    0.69
    urados
    0.63
    ት
    0.63
    an
    0.61
    quela
    0.60
    urium
    0.59
     stronę
    0.58
    忄
    0.58
    anju
    0.58
    POSITIVE LOGITS
    York
    0.85
     \
    0.84
     YORK
    0.77
     York
    0.74
     a
    0.71
     york
    0.70
     =
    0.67
     в
    0.67
    >%
    0.64
    york
    0.61
    Activations Density 0.001%

    No Known Activations