© 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. 43779
    Prev
    Next
    INDEX
    Explanations

    tokens before important

    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
    on
    1.21
    s
    1.05
    2
    0.96
    ע
    0.90
    ف
    0.90
    માં
    0.89
    ع
    0.88
    ما
    0.87
     on
    0.87
    at
    0.85
    POSITIVE LOGITS
     convertirse
    0.64
    š
    0.64
     Ubisoft
    0.64
     Și
    0.64
     Augusto
    0.63
    ()},
    0.63
    <
    0.63
    滘
    0.63
     conosci
    0.63
     ontwikkel
    0.63
    Activations Density 0.003%

    No Known Activations