© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38642
    Prev
    Next
    INDEX
    Explanations

    free-form text and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ,
    0.71
     efic
    0.68
    é
    0.66
     locali
    0.65
     logarithms
    0.64
     факторов
    0.63
     medici
    0.63
     pastries
    0.63
     κά
    0.62
     двери
    0.62
    POSITIVE LOGITS
    ى
    0.59
     );
    0.57
    ת
    0.56
    র্ত
    0.53
    ):(
    0.53
    خدام
    0.52
    нче
    0.52
    نوع
    0.51
    來的
    0.51
     Husky
    0.49
    Activations Density 0.001%

    No Known Activations