© 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. 24030
    Prev
    Next
    INDEX
    Explanations

    alongside

    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
    Negative Logits
    S
    0.32
    are
    0.31
    عی
    0.29
    sx
    0.29
    のである
    0.29
    threatening
    0.28
    erosion
    0.28
    Politics
    0.28
    home
    0.28
    よい
    0.27
    POSITIVE LOGITS
     Treiber
    0.34
     Benutz
    0.34
    ا
    0.33
    ва
    0.32
    да
    0.32
     På
    0.31
     Benutzer
    0.31
     فِي
    0.30
     وفي
    0.30
     installieren
    0.29
    Activations Density 0.002%

    No Known Activations