© 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. 194704
    Prev
    Next
    INDEX
    Explanations

    Mitt or Mithril

    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
    ilation
    0.45
    ళ
    0.39
    lwjglVersion
    0.38
    слан
    0.38
     الغ
    0.37
     Archibald
    0.36
    cado
    0.36
    Avant
    0.36
     Avant
    0.35
    quả
    0.35
    POSITIVE LOGITS
     pim
    0.41
     Bari
    0.40
    疸
    0.39
     spt
    0.39
    ὺ
    0.39
    ري
    0.38
     એમ
    0.38
    Mar
    0.37
     달
    0.37
     erm
    0.37
    Activations Density 0.000%

    No Known Activations