© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 23947
    Prev
    Next
    INDEX
    Explanations

    hematopoiesis, erythropoiesis, megakaryopoiesis

    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_10_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
    νης
    0.82
    的
    0.76
    ভাষায়
    0.71
    weapons
    0.70
    놁
    0.69
    بيق
    0.69
    ulaires
    0.69
    нося
    0.68
    ној
    0.67
    ის
    0.67
    POSITIVE LOGITS
     U
    0.96
    ,
    0.95
    "
    0.89
     E
    0.87
     M
    0.85
     W
    0.83
    h
    0.80
     T
    0.79
    r
    0.79
     I
    0.79
    Activations Density 0.001%

    No Known Activations