© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44024
    Prev
    Next
    INDEX
    Explanations

    woohoo exclamation

    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_3_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
    "
    0.79
    jší
    0.64
    (
    0.64
    N
    0.60
     element
    0.60
    usun
    0.59
    šte
    0.54
    hā
    0.54
     nació
    0.53
     mau
    0.52
    POSITIVE LOGITS
     θα
    0.66
    ש
    0.62
    ای
    0.59
     thời
    0.59
     ש
    0.57
     pulgadas
    0.57
    ры
    0.56
     phim
    0.56
     informacji
    0.56
     linguistique
    0.55
    Activations Density 0.000%

    No Known Activations