© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35967
    Prev
    Next
    INDEX
    Explanations

    Westminster Abbey

    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_31_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
     paragraph
    0.48
     Paragraph
    0.45
     psychic
    0.43
     paragraphs
    0.43
    綀
    0.41
     subparagraph
    0.39
    blusas
    0.38
     aliphatic
    0.38
    Paragraph
    0.38
    paragraph
    0.38
    POSITIVE LOGITS
    )^{
    0.43
     Westminster
    0.38
    ạc
    0.38
    ❙
    0.37
    QT
    0.36
    вости
    0.36
     टिक
    0.35
    isempty
    0.35
     lawmakers
    0.35
    किल
    0.35
    Activations Density 0.007%

    No Known Activations