© 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. 129854
    Prev
    Next
    INDEX
    Explanations

    diversity

    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
     Vara
    0.41
     нем
    0.39
     এখ
    0.37
    旪
    0.36
    aggreg
    0.35
    ตร์
    0.35
    렴
    0.35
     eighteenth
    0.35
     варі
    0.35
    拁
    0.35
    POSITIVE LOGITS
     diverse
    1.05
     다양
    1.03
     diversity
    1.02
     diversidad
    1.02
     Diverse
    0.98
     Diversity
    0.96
    多様
    0.96
    Diverse
    0.95
    多样
    0.95
    Diversity
    0.91
    Activations Density 0.008%

    No Known Activations