© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193945
    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
     prestazioni
    0.42
    ভৌম
    0.40
    ｓ
    0.39
     fik
    0.39
    ික
    0.38
     iman
    0.38
     Από
    0.38
     competitiveness
    0.38
     proizvođa
    0.38
     fungus
    0.37
    POSITIVE LOGITS
    Registro
    0.41
    सूर्य
    0.41
     rigorous
    0.40
     TU
    0.40
    眇
    0.39
     academically
    0.38
    涼
    0.38
     Patterson
    0.38
     व्याकरण
    0.37
    Sch
    0.36
    Activations Density 0.000%

    No Known Activations