© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145039
    Prev
    Next
    INDEX
    Explanations

    importance and benefit

    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_18_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
    ні
    0.50
    ція
    0.50
    τικού
    0.50
     tejto
    0.48
    கொ
    0.48
     souvent
    0.47
     dieses
    0.46
     gezond
    0.45
    ᅦ
    0.45
    Er
    0.44
    POSITIVE LOGITS
    CRM
    0.52
    宽高
    0.50
    XY
    0.49
    មើល
    0.49
     format
    0.48
     ప్రజా
    0.48
    闇
    0.48
     môn
    0.48
    image
    0.47
    图像
    0.47
    Activations Density 0.000%

    No Known Activations