© 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. 36797
    Prev
    Next
    INDEX
    Explanations

    flight delays and cancellations

    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
    ដាក់
    0.38
     گوش
    0.36
     podmín
    0.36
    រូប
    0.36
     int
    0.36
     postulates
    0.36
     gord
    0.35
    त्रे
    0.35
    塑
    0.35
     kèm
    0.34
    POSITIVE LOGITS
     delays
    0.41
     Delayed
    0.40
     crawling
    0.39
     delayed
    0.38
     Slots
    0.37
     Friendship
    0.37
     ارت
    0.37
     retras
    0.36
    delayed
    0.35
    Delayed
    0.35
    Activations Density 0.033%

    No Known Activations