© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40789
    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_11_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
     renov
    0.55
    s
    0.51
    ﺘ
    0.51
    iphatic
    0.51
    гать
    0.48
     चरणों
    0.48
    indrical
    0.48
     आवृत्ति
    0.47
    जान
    0.46
    il
    0.46
    POSITIVE LOGITS
     pouce
    0.58
    оп
    0.52
    فور
    0.50
    গি
    0.48
    🌊
    0.48
    지
    0.48
    декс
    0.47
    baixo
    0.46
    ленд
    0.46
    по
    0.46
    Activations Density 0.000%

    No Known Activations