© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144956
    Prev
    Next
    INDEX
    Explanations

    uis

    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_0_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
    ある
    1.53
     on
    1.35
    もちろん
    1.32
    ب
    1.31
    ไม่
    1.28
    د
    1.27
    この
    1.25
    6
    1.23
    ли
    1.21
    ться
    1.20
    POSITIVE LOGITS
    ла
    1.31
     is
    1.28
    ed
    1.23
    art
    1.14
    ită
    1.12
    нский
    1.06
    ছিলাম
    1.02
     in
    0.98
    นี
    0.98
    ो
    0.98
    Activations Density 0.000%

    No Known Activations