© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15144
    Prev
    Next
    INDEX
    Explanations

    Confucian Han Spring and Autumn

    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_40_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
    皎
    0.50
     Tang
    0.49
     Coal
    0.45
    唐
    0.44
    Tang
    0.44
     arab
    0.42
     唐
    0.41
    Tangent
    0.40
    🇶
    0.40
    ನಾ
    0.40
    POSITIVE LOGITS
    Han
    0.47
     Han
    0.46
     HAN
    0.44
    汉
    0.44
     SAT
    0.42
    春秋
    0.40
    HAN
    0.39
     han
    0.38
    丢失
    0.38
    SAT
    0.38
    Activations Density 0.029%

    No Known Activations