© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170986
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_56_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
     ========
    0.31
    および
    0.31
     إذا
    0.31
     ਅਤੇ
    0.30
    සිය
    0.29
     CGRectMake
    0.29
    または
    0.29
    azs
    0.29
    eils
    0.29
     вр
    0.29
    POSITIVE LOGITS
     disqual
    0.33
    ↵↵↵
    0.29
     ber
    0.29
     Programs
    0.28
    Programs
    0.28
     चुनौतीपूर्ण
    0.27
     Concert
    0.27
    သည်
    0.27
    <code>
    0.26
    ”
    0.26
    Activations Density 0.004%

    No Known Activations