© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64486
    Prev
    Next
    INDEX
    Explanations

    complexities of relationships

    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_41_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
    邦
    0.40
    WE
    0.38
    urlencoded
    0.37
    آ
    0.37
     bok
    0.37
    Kun
    0.37
    ўкі
    0.37
    젠
    0.37
     wish
    0.36
    গ্রামী
    0.36
    POSITIVE LOGITS
     дете
    0.40
    ậy
    0.37
    句
    0.37
     পৃথ
    0.36
     संचालन
    0.36
     দক্ষ
    0.35
     맞아
    0.35
     пользователи
    0.35
     полную
    0.35
     lấy
    0.34
    Activations Density 0.006%

    No Known Activations