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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132498
    Prev
    Next
    INDEX
    Explanations

    Japanese and Chinese names and words

    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_1_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
    т
    1.20
     що
    1.13
    ր
    0.99
    б
    0.96
    й
    0.93
    ِ
    0.85
    л
    0.84
    ш
    0.84
     что
    0.83
    त
    0.83
    POSITIVE LOGITS
    in
    1.54
    s
    1.32
    ad
    1.16
    h
    1.03
    o
    1.02
    .
    1.02
     ।
    1.01
     gái
    0.99
     avanti
    0.98
    em
    0.96
    Activations Density 0.000%

    No Known Activations