© 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. 125087
    Prev
    Next
    INDEX
    Explanations

    ostentatious display

    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
    f
    1.02
    c
    0.93
    d
    0.89
    l
    0.86
    g
    0.85
    s
    0.77
    ۲
    0.76
    2
    0.75
    b
    0.73
    m
    0.71
    POSITIVE LOGITS
     (
    0.75
    સ
    0.64
    ва
    0.63
    رسٹ
    0.63
    ua
    0.59
     बड़े
    0.59
     rusa
    0.59
    जहां
    0.58
    นิยม
    0.57
     बड़े
    0.56
    Activations Density 0.001%

    No Known Activations