© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26808
    Prev
    Next
    INDEX
    Explanations

    json processing

    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_10_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
     และ
    0.64
     t
    0.62
     medicines
    0.62
    :";
    0.62
    alal
    0.62
    al
    0.62
    rera
    0.62
    ras
    0.61
    ”!
    0.61
    rical
    0.61
    POSITIVE LOGITS
    ية
    0.76
     طريق
    0.62
    منى
    0.62
    مني
    0.61
    மா
    0.61
    Solving
    0.60
    kező
    0.59
     Semana
    0.59
    问
    0.58
    ことが
    0.57
    Activations Density 0.000%

    No Known Activations