© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50792
    Prev
    Next
    INDEX
    Explanations

    numbers following specific symbols

    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_31_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
    Ⓘ
    0.42
     bewegen
    0.42
    ineed
    0.41
     inú
    0.41
    *',
    0.40
     keh
    0.38
    АТО
    0.38
     ус
    0.38
    нибудь
    0.37
    сных
    0.37
    POSITIVE LOGITS
    閭
    0.40
    ങ്ങി
    0.39
    orgetown
    0.35
    opat
    0.34
     Upt
    0.33
     shelf
    0.33
    なく
    0.33
     NASCAR
    0.32
     Shelf
    0.32
     पूर्वी
    0.32
    Activations Density 0.006%

    No Known Activations