© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67518
    Prev
    Next
    INDEX
    Explanations

    postal service and related transport

    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_41_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
    úng
    0.39
    茈
    0.37
    ็ง
    0.37
     Bhubaneswar
    0.36
     McBride
    0.36
    笾
    0.35
    യ്
    0.35
     губер
    0.35
     Varanasi
    0.35
     Arithmetic
    0.35
    POSITIVE LOGITS
     postal
    1.05
    邮
    1.04
    郵
    0.99
     Postal
    0.96
     USPS
    0.95
     поч
    0.89
     Post
    0.89
    Postal
    0.88
     postale
    0.84
    postal
    0.84
    Activations Density 0.019%

    No Known Activations