© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130059
    Prev
    Next
    INDEX
    Explanations

    content warnings

    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_6_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
    د
    0.96
    iness
    0.93
    <h3>
    0.89
    ete
    0.87
    én
    0.86
    0.86
    ling
    0.86
    ère
    0.85
    ös
    0.83
    émie
    0.82
    POSITIVE LOGITS
    ס
    1.07
    s
    0.94
    ্স
    0.92
    ו
    0.90
    DLLEXPORT
    0.86
    ्राफी
    0.86
    ти
    0.86
    ﾌ
    0.86
    ”、
    0.84
    P
    0.83
    Activations Density 0.006%

    No Known Activations