© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243572
    Prev
    Next
    INDEX
    Explanations

    negatively impact

    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_40_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
     đưa
    0.52
    protect
    0.47
     लाता
    0.46
    毁
    0.45
    bringing
    0.44
     destruir
    0.43
     bringing
    0.43
     바꾸
    0.43
     değişt
    0.43
    puts
    0.42
    POSITIVE LOGITS
    珐
    0.40
    Р
    0.40
    Hourly
    0.40
     Hourly
    0.38
    Без
    0.38
     sans
    0.37
    ชาติ
    0.37
    であろう
    0.37
    概要
    0.35
     weekdays
    0.34
    Activations Density 0.004%

    No Known Activations