© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 80427
    Prev
    Next
    INDEX
    Explanations

    error handling

    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_29_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
     вироб
    0.38
    ולנד
    0.36
     ഗ്ര
    0.35
    deut
    0.35
    зом
    0.35
     Luh
    0.35
    Smile
    0.34
    廠
    0.34
    วี
    0.34
    ローマ
    0.33
    POSITIVE LOGITS
     करवाया
    0.45
     realizó
    0.39
     दिलाया
    0.38
     करती
    0.38
    했습니다
    0.34
     Immutable
    0.34
     প্রতিহিংস
    0.34
     yapan
    0.34
     करवाए
    0.34
     utilizó
    0.34
    Activations Density 0.007%

    No Known Activations