© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21300
    Prev
    Next
    INDEX
    Explanations

    self description

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Today
    0.45
     Today
    0.43
    否
    0.40
    Since
    0.40
    是一
    0.39
    Whenever
    0.38
     చ
    0.38
    Hoje
    0.38
    -#
    0.37
     오늘은
    0.36
    POSITIVE LOGITS
    得
    0.82
     different
    0.58
     得
    0.58
     gan
    0.58
     past
    0.57
    different
    0.51
     simple
    0.50
    として
    0.47
     speaking
    0.47
    ได้
    0.44
    Activations Density 0.004%

    No Known Activations