© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180136
    Prev
    Next
    INDEX
    Explanations

    intensifying negative aspects

    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
     entitles
    0.45
    >+</
    0.38
     सिक्
    0.38
    ｿ
    0.38
    javab
    0.38
     Utils
    0.38
     트리
    0.37
    醝
    0.37
     美
    0.37
     事
    0.37
    POSITIVE LOGITS
     কোন্‌
    0.43
     vuelta
    0.38
    arco
    0.37
    袍
    0.37
     caderno
    0.36
     esigen
    0.36
     rather
    0.36
    而非
    0.36
    ionu
    0.35
    Rather
    0.35
    Activations Density 0.015%

    No Known Activations