© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174100
    Prev
    Next
    INDEX
    Explanations

    using ( or open (

    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_20_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
    iteracy
    0.43
     цвето
    0.42
     оцен
    0.42
     విజ
    0.40
    atah
    0.40
     пробле
    0.39
     направ
    0.39
    ୌ
    0.39
     vastly
    0.39
     количестве
    0.39
    POSITIVE LOGITS
     esk
    0.44
     dern
    0.42
     prenot
    0.41
     afsl
    0.41
    وراق
    0.41
     đợi
    0.40
     slid
    0.40
     ставок
    0.40
    停车场
    0.40
     virg
    0.40
    Activations Density 0.000%

    No Known Activations