© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43902
    Prev
    Next
    INDEX
    Explanations

    cups and championships

    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_3_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
     was
    0.73
     can
    0.68
    a
    0.67
     restraining
    0.64
    the
    0.62
    IÓN
    0.61
    ihe
    0.61
    i
    0.61
     කොට
    0.61
    ILE
    0.59
    POSITIVE LOGITS
    ре
    0.75
    ра
    0.66
    ри
    0.61
    р
    0.57
    ّر
    0.57
    ду
    0.55
    ز
    0.55
    то
    0.54
    ering
    0.54
     uprisings
    0.54
    Activations Density 0.000%

    No Known Activations