© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27223
    Prev
    Next
    INDEX
    Explanations

    berberine, resveratrol, metformin, sirtuins, rhubarb

    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
    ä
    0.82
    är
    0.78
    ط
    0.73
     How
    0.66
    šć
    0.66
    iz
    0.65
    л
    0.65
    人
    0.65
    <unused1858>
    0.64
     বেশিরভাগ
    0.64
    POSITIVE LOGITS
     aband
    0.66
     zmiany
    0.63
    दारा
    0.62
    ത്യാ
    0.62
    サングラス
    0.61
     gesam
    0.61
    κρι
    0.61
     μιας
    0.61
    ದಾರ
    0.60
    ハート
    0.59
    Activations Density 0.011%

    No Known Activations