© 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. 141463
    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_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
    d
    0.62
    ated
    0.61
    ically
    0.60
    ative
    0.57
    ad
    0.57
     اختبار
    0.56
    ally
    0.54
     F
    0.54
    ata
    0.53
     Weir
    0.52
    POSITIVE LOGITS
    لیکن
    0.61
     keuangan
    0.57
    டுகின்றன
    0.55
     ngunit
    0.54
     mutta
    0.54
     tačiau
    0.54
     بدان
    0.54
    তাহাকে
    0.54
     Igreja
    0.53
    েজ
    0.53
    Activations Density 0.000%

    No Known Activations