© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121785
    Prev
    Next
    INDEX
    Explanations

    acetylsalicylic acid

    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_3_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
    い
    0.82
    始めた
    0.75
    ため
    0.70
     Dự
    0.70
    اریخ
    0.70
    ِی
    0.70
     Tháng
    0.69
    ުރ
    0.68
    گذاری
    0.66
    اہے
    0.66
    POSITIVE LOGITS
     on
    1.05
     in
    0.75
    0
    0.72
    ه
    0.68
    s
    0.66
    ע
    0.64
    or
    0.64
    nement
    0.63
    生
    0.62
    ken
    0.61
    Activations Density 0.000%

    No Known Activations