© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137779
    Prev
    Next
    INDEX
    Explanations

    verb endings in multiple scripts

    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_12_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
     ನ್ಯಾಯ
    0.53
     heterozygous
    0.44
    chyné
    0.43
     mạch
    0.42
     کورٹ
    0.42
    
    0.41
     своїх
    0.41
     پہلے
    0.40
     jego
    0.40
    เมนต์
    0.40
    POSITIVE LOGITS
     Suche
    0.47
    a
    0.45
     Face
    0.44
    ag
    0.43
     Free
    0.42
     Einf
    0.41
    s
    0.41
    et
    0.40
    af
    0.40
    op
    0.40
    Activations Density 0.016%

    No Known Activations