© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10043
    Prev
    Next
    INDEX
    Explanations

    cerebrospinal fluid and conditions

    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_13_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
    าม
    0.62
     História
    0.55
     Cá
    0.54
    امة
    0.52
    ξ
    0.50
    áneas
    0.50
     chá
    0.49
    ímos
    0.49
    día
    0.48
    美
    0.48
    POSITIVE LOGITS
     Kazakh
    0.51
     obraz
    0.51
    簪
    0.51
     Peabody
    0.50
     dire
    0.50
     Slovak
    0.50
     donkey
    0.49
     daftar
    0.48
     lipoprotein
    0.48
     walnut
    0.48
    Activations Density 0.000%

    No Known Activations