© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161919
    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_31_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
     sacr
    0.38
    paw
    0.37
     동안
    0.36
    पीजी
    0.36
     goreng
    0.35
     outperforms
    0.35
     $[\
    0.34
     chops
    0.34
     characterized
    0.34
    동안
    0.34
    POSITIVE LOGITS
     Vulcan
    0.40
    ঙ্খ
    0.38
     सफलता
    0.38
    粔
    0.38
    洺
    0.38
     кукуру
    0.37
     puedes
    0.37
     Liability
    0.37
    न्स
    0.37
    可以使用
    0.37
    Activations Density 0.003%

    No Known Activations