© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193343
    Prev
    Next
    INDEX
    Explanations

    immediate after

    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_9_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
    it
    0.89
    is
    0.84
    I
    0.83
    د
    0.80
    OS
    0.76
    ो
    0.73
     पहला
    0.73
    ede
    0.72
    ä
    0.71
    و
    0.70
    POSITIVE LOGITS
    အတူ
    0.95
     as
    0.94
    كم
    0.93
     were
    0.91
    كس
    0.89
     integrate
    0.89
     podem
    0.89
    দের
    0.88
    ות
    0.85
     mitigate
    0.85
    Activations Density 0.007%

    No Known Activations