© 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. 26298
    Prev
    Next
    INDEX
    Explanations

    BibTeX and bibs

    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
    。
    0.90
     Utilisez
    0.75
    。「
    0.70
    。"
    0.69
    ט
    0.69
    ।
    0.66
     h
    0.66
     。
    0.65
    。<
    0.65
    酒
    0.61
    POSITIVE LOGITS
    c
    0.72
    ه
    0.64
     resolv
    0.61
    ва
    0.58
    ‌تر
    0.58
     preconceived
    0.58
    e
    0.57
     fitter
    0.56
     stung
    0.56
     bởi
    0.55
    Activations Density 0.001%

    No Known Activations