© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207176
    Prev
    Next
    INDEX
    Explanations

    hobby or passion, hackers monetize

    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_10_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
     ROUILLER
    0.51
    燾
    0.49
    ण्यासाठी
    0.49
    ا
    0.48
    mals
    0.48
    ຕ້ອງການ
    0.48
    ниями
    0.47
    ركات
    0.47
    ట్లు
    0.47
    褻
    0.47
    POSITIVE LOGITS
     copy
    0.47
     kernel
    0.47
     quirks
    0.46
     ベ
    0.46
     payback
    0.46
     belly
    0.45
     killing
    0.43
     avenue
    0.43
     leaving
    0.43
     arches
    0.42
    Activations Density 0.000%

    No Known Activations