© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203610
    Prev
    Next
    INDEX
    Explanations

    reimbursement request or fee

    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_6_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
     údaje
    0.70
     zvyš
    0.64
     vó
    0.64
    لي
    0.61
    家伙
    0.59
     هي
    0.59
    <unused2113>
    0.58
     mivel
    0.58
     pruž
    0.57
    بي
    0.56
    POSITIVE LOGITS
    as
    1.05
    지
    0.79
    at
    0.79
    inę
    0.72
    in
    0.70
    ar
    0.68
    bread
    0.67
    is
    0.67
    ac
    0.67
    o
    0.66
    Activations Density 0.001%

    No Known Activations