© 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. 37088
    Prev
    Next
    INDEX
    Explanations

    composers

    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
    Ton
    0.42
    トキ
    0.42
    TSP
    0.41
     N
    0.39
     Romeo
    0.39
    iguous
    0.37
    Мар
    0.37
     नर्मदा
    0.37
    Peripheral
    0.37
    pbs
    0.37
    POSITIVE LOGITS
     Denton
    0.42
     Mas
    0.41
     mas
    0.40
    oland
    0.39
    umas
    0.39
    odan
    0.39
     од
    0.38
    푸
    0.38
    mas
    0.38
     rug
    0.38
    Activations Density 0.001%

    No Known Activations