© 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. 31032
    Prev
    Next
    INDEX
    Explanations

    measurements and units

    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
     등의
    0.41
    などの
    0.37
    等的
    0.37
    Coffee
    0.36
    Gol
    0.35
     等
    0.35
    地的
    0.34
    Franc
    0.34
    equip
    0.33
    动漫
    0.33
    POSITIVE LOGITS
    ંટણી
    0.36
     الوحد
    0.34
    ᓲ
    0.34
    ſed
    0.33
    ंटर
    0.33
    ដែលមាន
    0.33
    စိတ်အပိုင်း
    0.33
    ត្រូវ
    0.32
    。",
    0.32
    ebles
    0.32
    Activations Density 2.048%

    No Known Activations