© 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. 179896
    Prev
    Next
    INDEX
    Explanations

    languages and places

    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
     Z
    0.45
    MZ
    0.43
     F
    0.39
     mz
    0.38
     Fr
    0.38
    venu
    0.37
     MZ
    0.37
     sportsbook
    0.37
    র্গের
    0.36
     Madras
    0.36
    POSITIVE LOGITS
     لال
    0.41
     جمله
    0.40
    geant
    0.39
    StackNavigator
    0.38
     Bagan
    0.38
    ppi
    0.37
    慌
    0.37
    onal
    0.37
    لال
    0.36
    Hit
    0.36
    Activations Density 0.004%

    No Known Activations