© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232834
    Prev
    Next
    INDEX
    Explanations

    foreign language markers

    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_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    1.13
    ↵↵
    0.93
    )
    0.93
     It
    0.79
    变
    0.75
     for
    0.74
     to
    0.73
     been
    0.71
    י
    0.70
    可持续
    0.70
    POSITIVE LOGITS
     Tattha
    0.98
     Aeonium
    0.94
     Бүген
    0.91
     APIDC
    0.89
     आरबीआई
    0.87
    g
    0.86
    nDims
    0.85
    impanan
    0.84
     Ettha
    0.83
    ungkinan
    0.83
    Activations Density 0.000%

    No Known Activations