© 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. 37386
    Prev
    Next
    INDEX
    Explanations

    soul, spirit, heart

    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
    makers
    0.61
    pers
    0.60
    š
    0.59
     అవు
    0.59
     کر
    0.59
     طور
    0.58
     해
    0.57
     پس
    0.57
     interests
    0.56
     ਡ
    0.55
    POSITIVE LOGITS
    т
    0.73
    h
    0.72
    t
    0.71
    त
    0.68
    о
    0.62
     okolo
    0.61
    ય
    0.60
    ட்
    0.59
    ન
    0.58
    տ
    0.58
    Activations Density 0.001%

    No Known Activations