© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88629
    Prev
    Next
    INDEX
    Explanations

    wilting wildflower

    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_3_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
    لي
    1.08
    يل
    1.04
    在
    0.93
    n
    0.92
    ci
    0.87
    ين
    0.86
    :
    0.84
    ká
    0.84
    ير
    0.80
     في
    0.80
    POSITIVE LOGITS
    s
    1.19
    ی
    1.14
    یی
    0.91
    ים
    0.88
    ای
    0.86
    ید
    0.83
     تاریخ
    0.80
    اوی
    0.78
    াধিক
    0.78
    える
    0.76
    Activations Density 0.001%

    No Known Activations