© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54483
    Prev
    Next
    INDEX
    Explanations

    GWAS and genetic risk association

    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_31_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
    PhysRev
    0.37
     AppDelegate
    0.36
    Magnet
    0.34
    DIVISION
    0.34
     δι
    0.34
    我在
    0.34
    男友
    0.34
     اوس
    0.34
    犮
    0.34
    ovir
    0.33
    POSITIVE LOGITS
     destined
    0.41
     predisposition
    0.41
     Reply
    0.40
     sever
    0.39
     sil
    0.38
     whe
    0.38
     Khal
    0.38
     susceptibility
    0.37
     susceptibles
    0.37
     privacidad
    0.37
    Activations Density 0.000%

    No Known Activations