© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 80297
    Prev
    Next
    INDEX
    Explanations

    special session or issue

    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_29_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
    тара
    0.33
    request
    0.32
    Ƅ
    0.31
    received
    0.31
     marts
    0.31
    瓤
    0.30
    dotted
    0.30
     facilita
    0.30
    science
    0.30
    位相
    0.30
    POSITIVE LOGITS
     doméstica
    0.35
    Fly
    0.34
    票
    0.34
     YOUR
    0.33
    ütün
    0.33
     Wanted
    0.33
     Waik
    0.33
     Kait
    0.33
     sensibles
    0.32
     unharmed
    0.32
    Activations Density 0.002%

    No Known Activations