© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8843
    Prev
    Next
    INDEX
    Explanations

    initialization of weights/biases

    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_13_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
    ENTAL
    0.20
    ା
    0.19
    middleware
    0.18
    ान
    0.18
    Email
    0.18
    ENT
    0.17
    of
    0.17
    HttpClient
    0.17
    ma
    0.17
    gus
    0.16
    POSITIVE LOGITS
    บอก
    0.19
    ฟ
    0.19
     эсеп
    0.19
     хочет
    0.19
     рядом
    0.19
     Amherst
    0.18
     brzo
    0.18
    叕
    0.18
     zarządz
    0.18
    শোর
    0.18
    Activations Density 0.006%

    No Known Activations