© 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. 60016
    Prev
    Next
    INDEX
    Explanations

    ages and family titles

    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
    EN
    0.55
    🐾
    0.54
    핌
    0.49
    𝘿
    0.49
    diet
    0.48
    🦀
    0.48
    Pinterest
    0.48
    e
    0.48
    diabetes
    0.47
     TRANSFER
    0.47
    POSITIVE LOGITS
     novels
    0.61
     도시
    0.54
     jovens
    0.53
     alcohols
    0.52
    ica
    0.52
     lỗi
    0.52
    ہوری
    0.52
    uzo
    0.52
    astan
    0.51
     Novels
    0.51
    Activations Density 0.031%

    No Known Activations