© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195667
    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_27_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
     基于
    0.41
    lika
    0.41
     разработки
    0.41
     মর্
    0.40
     détermine
    0.40
    軼
    0.40
     basados
    0.39
     legít
    0.39
     ವಿಧಾನ
    0.39
     ਤੁ
    0.39
    POSITIVE LOGITS
     Commun
    0.44
     Commiss
    0.43
     City
    0.42
     freel
    0.39
     Feuer
    0.38
    ₂
    0.38
     called
    0.37
     wad
    0.37
     Colleges
    0.37
     Rol
    0.36
    Activations Density 0.000%

    No Known Activations