© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196472
    Prev
    Next
    INDEX
    Explanations

    Intel Atom and Celeron processors

    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_15_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
    ური
    0.60
     roky
    0.55
    Ⲟ
    0.55
    изо
    0.55
    меся
    0.54
     Ако
    0.54
    сив
    0.54
    nienie
    0.54
    Ə
    0.54
    мя
    0.52
    POSITIVE LOGITS
     o
    0.48
     Barack
    0.48
     ous
    0.47
     s
    0.46
     t
    0.45
     Sch
    0.44
     stra
    0.43
     Piaget
    0.43
     leadership
    0.43
     cust
    0.43
    Activations Density 0.000%

    No Known Activations