© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129612
    Prev
    Next
    INDEX
    Explanations

    Basque language phrases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    堃
    0.46
    ukan
    0.42
    頬
    0.39
    เฉ
    0.39
    Sue
    0.39
    銷
    0.38
    <0xA5>
    0.38
    Joel
    0.38
    ქ
    0.37
    зу
    0.37
    POSITIVE LOGITS
     Tir
    0.45
     NEC
    0.43
     Tog
    0.43
     ToString
    0.42
     ATF
    0.41
     ESA
    0.41
    iza
    0.41
    etsa
    0.40
     ere
    0.40
     madde
    0.40
    Activations Density 0.005%

    No Known Activations