© 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. 226727
    Prev
    Next
    INDEX
    Explanations

    goals

    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
    0.94
    ip
    0.73
     It
    0.72
     I
    0.69
    If
    0.66
    It
    0.64
    \
    0.64
    </b>
    0.62
    ess
    0.61
     production
    0.61
    POSITIVE LOGITS
    𝒈
    0.87
     聞い
    0.80
     Każ
    0.78
     Otros
    0.77
     administers
    0.76
     Después
    0.75
     unmist
    0.75
     Ри
    0.75
    𝗖
    0.75
     পদ্ধতিতে
    0.75
    Activations Density 0.005%

    No Known Activations