© 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. 213080
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    們
    1.63
    们
    1.55
    ๆ
    1.43
    们的
    1.38
     ๆ
    1.22
    들은
    1.18
    들에
    1.16
    들의
    1.15
    들이
    1.13
    들
    1.13
    POSITIVE LOGITS
    কেও
    0.56
    কে
    0.55
    ക്ക്
    0.47
     arasında
    0.47
    ക്ക്‌
    0.43
    ගේ
    0.43
    ၏
    0.43
     વચ્ચે
    0.42
     ਦੀ
    0.42
     aras
    0.41
    Activations Density 0.000%

    No Known Activations