© 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. 31055
    Prev
    Next
    INDEX
    Explanations

    San

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.48
    alpha
    0.43
    helf
    0.40
    Bernard
    0.39
    茨
    0.39
    यत
    0.39
    DIALOG
    0.39
    Alpha
    0.38
     меди
    0.38
    Nast
    0.38
    POSITIVE LOGITS
    ému
    0.43
    сності
    0.41
    uda
    0.41
     칸
    0.38
     UIImage
    0.38
     vzduchu
    0.37
     العق
    0.36
     втор
    0.36
    巾
    0.35
    imide
    0.35
    Activations Density 0.000%

    No Known Activations