© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88641
    Prev
    Next
    INDEX
    Explanations

    fit, snug, secure, foam, lined

    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_11_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
    0
    0.80
    3
    0.74
    1
    0.70
    2
    0.64
    4
    0.61
    7
    0.61
    لت
    0.60
    8
    0.60
    tr
    0.59
    チ
    0.58
    POSITIVE LOGITS
     toolPath
    0.61
     തുടങ്ങി
    0.58
     gleichen
    0.57
    牞
    0.56
    咶
    0.55
     kasar
    0.54
     desse
    0.53
    龕
    0.53
     आंसर
    0.53
     yüks
    0.53
    Activations Density 0.025%

    No Known Activations