© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135548
    Prev
    Next
    INDEX
    Explanations

    Dutch definite articles

    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_6_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
     basilaires
    0.92
     überprü
    0.87
    ம்
    0.83
    ни
    0.80
    س
    0.79
     konkre
    0.75
    ه
    0.73
    面
    0.73
    ار
    0.72
    𝐞
    0.72
    POSITIVE LOGITS
    to
    1.55
    ,
    1.24
    w
    1.11
     to
    1.09
    D
    1.09
    F
    1.03
    X
    1.03
    c
    1.02
    H
    1.02
    P
    1.00
    Activations Density 0.000%

    No Known Activations