© 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. 124535
    Prev
    Next
    INDEX
    Explanations

    befitting

    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
    s
    0.65
    ंच्या
    0.63
    ю
    0.62
    ्ट
    0.62
    ↵
    0.61
     handbag
    0.56
    т
    0.55
    ни
    0.55
    ри
    0.55
    d
    0.54
    POSITIVE LOGITS
    ال
    0.82
    and
    0.76
     alemán
    0.70
    Ա
    0.68
     کل
    0.66
     οποίο
    0.66
    aua
    0.65
     ομά
    0.64
     eléctricos
    0.64
     Ад
    0.63
    Activations Density 0.000%

    No Known Activations