© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35234
    Prev
    Next
    INDEX
    Explanations

    refer to official documentation

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mg
    0.61
    Assessment
    0.57
    expertise
    0.57
    t
    0.54
    ugs
    0.54
    ugg
    0.52
    Feedback
    0.52
    appreciated
    0.50
    v
    0.50
    urers
    0.50
    POSITIVE LOGITS
     izango
    0.64
     kumpulan
    0.63
     sarà
    0.59
     nakon
    0.57
     dostup
    0.56
     lintas
    0.55
     dopo
    0.55
     setelah
    0.55
     peraturan
    0.55
     saranno
    0.54
    Activations Density 0.003%

    No Known Activations