© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168649
    Prev
    Next
    INDEX
    Explanations

    innate immunity defense

    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_34_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
    Temperature
    0.46
     temperature
    0.41
     Temperature
    0.38
     깨
    0.38
     sterility
    0.38
     설정
    0.37
    뭄
    0.37
    騨
    0.37
     command
    0.37
    Updater
    0.37
    POSITIVE LOGITS
    ポーチ
    0.44
    CATEG
    0.39
     screening
    0.39
     bottlene
    0.39
     Оле
    0.38
     videocon
    0.38
    Cup
    0.38
     prima
    0.38
     ਵੱ
    0.37
    ᖅ
    0.37
    Activations Density 0.001%

    No Known Activations