© 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. 194720
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    Negative Logits
    甯
    0.48
    nms
    0.47
    寜
    0.45
    宁
    0.45
    Nina
    0.45
     Nina
    0.43
     Nikki
    0.42
    Ning
    0.41
     NIS
    0.41
    寧
    0.40
    POSITIVE LOGITS
    htu
    0.40
    terre
    0.39
     Rodrigo
    0.37
     يكن
    0.37
     Geräte
    0.36
     owe
    0.36
    helves
    0.36
    ören
    0.35
    米
    0.35
    viv
    0.35
    Activations Density 0.000%

    No Known Activations