© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181138
    Prev
    Next
    INDEX
    Explanations

    code, items, and toys

    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_29_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
    بعة
    0.41
    sembled
    0.40
     fileobj
    0.38
    structor
    0.38
    锹
    0.38
    puted
    0.37
    叵
    0.37
     ইন্দুর
    0.37
     қ
    0.35
    converter
    0.35
    POSITIVE LOGITS
     SHIPPING
    0.40
     நிமிட
    0.39
     needing
    0.38
     կար
    0.38
     മാറ
    0.38
     COULD
    0.38
     Kommune
    0.38
     требует
    0.37
     checking
    0.37
     being
    0.37
    Activations Density 0.001%

    No Known Activations