© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134396
    Prev
    Next
    INDEX
    Explanations

    local festivals

    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_37_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
    cors
    0.41
    nav
    0.40
    played
    0.39
     स्वि
    0.37
    icals
    0.37
     khal
    0.37
    chor
    0.36
    喬
    0.36
     wak
    0.36
    holiday
    0.36
    POSITIVE LOGITS
     बैठक
    0.41
     Packs
    0.40
    ('[
    0.39
     tubules
    0.39
     ব্য
    0.38
    ිරි
    0.38
     Deter
    0.37
     مجموع
    0.37
    这也是
    0.37
     заседа
    0.36
    Activations Density 0.001%

    No Known Activations