© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192348
    Prev
    Next
    INDEX
    Explanations

    St. James's Park

    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_4_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
    m
    0.90
    g
    0.87
    in
    0.83
     .
    0.80
    ্জ
    0.74
    ↵
    0.73
    ات
    0.70
    u
    0.70
    f
    0.70
    j
    0.70
    POSITIVE LOGITS
    োক্ত
    0.72
    τή
    0.71
    aloko
    0.68
     demikian
    0.67
    Вот
    0.67
    К
    0.67
    ン
    0.66
     мощность
    0.65
     حقی
    0.64
    もら
    0.64
    Activations Density 0.000%

    No Known Activations