© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83154
    Prev
    Next
    INDEX
    Explanations

    NYC or New York City

    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_0_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
    ك
    2.34
     on
    1.82
    ة
    1.73
    其他
    1.71
    ف
    1.70
    ка
    1.66
    to
    1.59
    أ
    1.54
    ви
    1.51
    아
    1.43
    POSITIVE LOGITS
    '
    1.97
    s
    1.63
    st
    1.54
    l
    1.49
    น
    1.45
    いた
    1.41
    n
    1.40
     I
    1.34
    d
    1.33
    r
    1.29
    Activations Density 0.000%

    No Known Activations