© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225644
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    นวน
    0.45
    collation
    0.44
    ว
    0.44
    触发
    0.44
     தமிழ்
    0.43
    ტორი
    0.43
    퐶
    0.42
     plowed
    0.42
    푠
    0.42
    孩子们
    0.42
    POSITIVE LOGITS
     Дер
    0.50
    மிட
    0.44
     ಸಂಪ
    0.44
     doubly
    0.43
     commensurate
    0.43
     હેઠળ
    0.43
     Win
    0.42
     dispone
    0.42
     Suk
    0.42
     Tosh
    0.42
    Activations Density 0.000%

    No Known Activations