© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48040
    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_31_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
     diminution
    0.35
    DesignTime
    0.33
    𝖺
    0.33
    ulio
    0.33
    '.$
    0.32
     கிமு
    0.32
    ijos
    0.32
    anato
    0.32
    (`${
    0.31
     অনুপ্র
    0.31
    POSITIVE LOGITS
    xido
    0.36
    ঙ্গার
    0.35
     ори
    0.35
     બનાવે
    0.34
     ऊ
    0.34
     Orientation
    0.34
     Orient
    0.34
     Functions
    0.33
     BUS
    0.33
    腫
    0.33
    Activations Density 0.000%

    No Known Activations