© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198641
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    A
    0.64
     άνθρω
    0.64
    altung
    0.63
    amentos
    0.58
     sintering
    0.58
     склад
    0.57
    0.57
    روں
    0.56
    ing
    0.55
     Startup
    0.55
    POSITIVE LOGITS
    ار
    0.88
    ล
    0.79
    স
    0.77
    ’
    0.74
    स
    0.73
    る
    0.71
    $,
    0.71
    ア
    0.71
    트
    0.71
    ट
    0.70
    Activations Density 0.000%

    No Known Activations