© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6892
    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_39_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
     Народ
    0.39
     الشعب
    0.38
    🇲
    0.37
     Bisby
    0.36
    bibfnamefont
    0.36
     Escuela
    0.36
     Calle
    0.36
    ໄປ
    0.35
     Señ
    0.35
     кафед
    0.35
    POSITIVE LOGITS
    Document
    0.37
    赉
    0.36
    Doc
    0.35
    doc
    0.35
     pent
    0.35
     doc
    0.34
     Pneum
    0.33
     weekly
    0.33
     Document
    0.33
    niak
    0.33
    Activations Density 0.002%

    No Known Activations