© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47354
    Prev
    Next
    INDEX
    Explanations

    years ago

    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_10_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
    '
    0.37
     have
    0.34
    ı
    0.34
    ী
    0.33
    aka
    0.32
     are
    0.32
    E
    0.30
    have
    0.29
     badger
    0.27
     hebben
    0.26
    POSITIVE LOGITS
     SPMs
    0.31
     RTL
    0.31
     във
    0.29
    ര്‍ഷ
    0.29
    ᱓
    0.28
     NPE
    0.28
     Влади
    0.28
    一年
    0.28
     TRPV
    0.28
    ዔ
    0.27
    Activations Density 0.003%

    No Known Activations