© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140068
    Prev
    Next
    INDEX
    Explanations

    what questions about passions or impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    datab
    0.46
     люди
    0.38
    뭘
    0.37
     hopes
    0.37
    等級
    0.35
    自我
    0.35
    oxal
    0.35
     그걸
    0.35
     사람들이
    0.35
     devices
    0.35
    POSITIVE LOGITS
    nań
    0.39
     mantiene
    0.39
     Diện
    0.39
     aussch
    0.38
    媤
    0.38
    Ẫ
    0.38
    Feels
    0.38
    ごはん
    0.37
    lid
    0.36
    amant
    0.36
    Activations Density 0.005%

    No Known Activations