© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36931
    Prev
    Next
    INDEX
    Explanations

    energy metabolism

    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_11_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
     ರಾಜ
    0.57
    出的
    0.54
     ambientales
    0.52
    夗
    0.52
     Люди
    0.51
     люди
    0.50
    岕
    0.50
     EMERG
    0.49
     из
    0.48
     человек
    0.48
    POSITIVE LOGITS
    Kh
    0.46
    тім
    0.46
     traitor
    0.46
    jPanel
    0.45
    脂肪
    0.45
    stup
    0.45
    [
    0.45
    ブ
    0.44
     metabolism
    0.44
    Four
    0.44
    Activations Density 0.080%

    No Known Activations