© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39862
    Prev
    Next
    INDEX
    Explanations

    magnetism, geobræ, gefällt

    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_3_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
    ك
    0.87
    ט
    0.79
    ي
    0.77
    ი
    0.77
    ።
    0.75
     argumentos
    0.71
    0.71
    ।
    0.70
    ۔
    0.70
     eigenvectors
    0.69
    POSITIVE LOGITS
    lettes
    0.63
    vey
    0.59
    ardom
    0.58
    have
    0.58
    flakes
    0.57
    hear
    0.56
    NIS
    0.56
    le
    0.55
    hold
    0.55
    ্ম্ম
    0.55
    Activations Density 0.003%

    No Known Activations