© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154519
    Prev
    Next
    INDEX
    Explanations

    fly log Logan

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Dragons
    0.43
     dragons
    0.42
    Dragon
    0.41
     বলিয়
    0.40
     Della
    0.40
     Dragon
    0.39
    جين
    0.39
     डिल
    0.38
     デ
    0.36
    South
    0.36
    POSITIVE LOGITS
     fly
    0.58
     Fly
    0.58
     Logan
    0.52
    Fly
    0.52
    fly
    0.50
    log
    0.48
    Logan
    0.45
     log
    0.45
    LOG
    0.44
    логии
    0.42
    Activations Density 0.068%

    No Known Activations