© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66905
    Prev
    Next
    INDEX
    Explanations

    tsuderes, T.S. Eliot, TSMC, proper nouns

    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_41_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
    atalog
    0.39
     bf
    0.39
     سوری
    0.39
     সাইফুদ্দিন
    0.39
    ългар
    0.39
    ceğ
    0.38
     عر
    0.38
    狭
    0.38
    uhà
    0.37
    ರೀಕ್ಷ
    0.37
    POSITIVE LOGITS
     Eliot
    0.50
     гла
    0.49
    Eli
    0.49
     gl
    0.45
     auditor
    0.44
     GL
    0.43
     엘
    0.40
    制
    0.40
    GL
    0.39
     LG
    0.38
    Activations Density 0.000%

    No Known Activations