© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32613
    Prev
    Next
    INDEX
    Explanations

    right now

    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_7_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
    '.$
    0.63
    this
    0.59
    that
    0.54
    Бы
    0.53
     Barley
    0.52
    I
    0.52
    ను
    0.52
    "，
    0.51
    ς
    0.50
    Бе
    0.49
    POSITIVE LOGITS
     et
    0.89
     up
    0.80
    to
    0.78
     or
    0.77
     astronomer
    0.73
    in
    0.71
    ad
    0.68
    ق
    0.68
    at
    0.67
     aversion
    0.66
    Activations Density 0.004%

    No Known Activations