© 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. 204069
    Prev
    Next
    INDEX
    Explanations

    processing information or events

    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
     I
    0.97
     has
    0.88
    C
    0.83
    ain
    0.80
    t
    0.79
    {
    0.79
    Ü
    0.78
     heeft
    0.76
    ية
    0.75
    sl
    0.75
    POSITIVE LOGITS
    지
    0.89
    are
    0.84
    ために
    0.84
    is
    0.84
    at
    0.76
    ЕЛЬ
    0.74
    os
    0.73
    ლება
    0.73
    지에
    0.72
    قوم
    0.71
    Activations Density 0.003%

    No Known Activations