© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24221
    Prev
    Next
    INDEX
    Explanations

    Monster Manual, Monster Kid, monster hunters

    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_10_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
     سي
    0.26
    어
    0.23
    𝗱
    0.22
     се
    0.22
    ୍ର
    0.21
     ଦ
    0.21
     أس
    0.20
    ソ
    0.19
     بي
    0.19
     creș
    0.19
    POSITIVE LOGITS
     GridPane
    0.24
    🚔
    0.21
     Dimension
    0.20
     Packard
    0.20
    fieldset
    0.20
    kses
    0.19
    🔳
    0.19
    configurable
    0.19
     playwright
    0.19
    جا
    0.19
    Activations Density 0.011%

    No Known Activations