© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143804
    Prev
    Next
    INDEX
    Explanations

    mass spectrometry

    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_46_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
     उत्तरा
    0.39
     साथी
    0.38
    食堂
    0.38
    ambda
    0.38
    细
    0.38
     Telescope
    0.38
     Cedex
    0.38
    ussie
    0.37
    疊
    0.37
    रायपुर
    0.37
    POSITIVE LOGITS
     анализ
    0.48
     analysis
    0.47
     analý
    0.46
    analysis
    0.45
    Analysis
    0.44
     analyse
    0.43
     analiz
    0.43
     Analysis
    0.42
     analys
    0.41
     광
    0.41
    Activations Density 0.000%

    No Known Activations