© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28713
    Prev
    Next
    INDEX
    Explanations

    assets directory contents

    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_40_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
     Ice
    0.43
    ๆ
    0.43
    تام
    0.42
     Dried
    0.40
     ль
    0.39
    兵
    0.39
     throwIfNotFound
    0.38
     ice
    0.38
     carefree
    0.38
    ਦ
    0.38
    POSITIVE LOGITS
     Fala
    0.40
     Vide
    0.39
     recevoir
    0.39
    影像
    0.38
    pio
    0.38
    ⊠
    0.37
    ullo
    0.36
    ulla
    0.36
    Vide
    0.36
    accounts
    0.35
    Activations Density 0.001%

    No Known Activations