© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59009
    Prev
    Next
    INDEX
    Explanations

    full of life

    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_11_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
    t
    0.99
    es
    0.96
    ed
    0.86
    to
    0.80
    is
    0.76
    ت
    0.75
    of
    0.73
    lessness
    0.72
    т
    0.70
    lite
    0.69
    POSITIVE LOGITS
    و
    0.70
    ડ
    0.66
    ढ
    0.65
     درخواست
    0.63
    貸款
    0.63
     خداوند
    0.63
    ртка
    0.63
    arien
    0.62
     궁금
    0.61
    퐫
    0.60
    Activations Density 0.005%

    No Known Activations