© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88774
    Prev
    Next
    INDEX
    Explanations

    RoHS, toxic, China, Canton

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    w
    0.62
    i
    0.56
    wych
    0.55
    centes
    0.55
    l
    0.54
     даст
    0.53
    x
    0.53
    0.52
    d
    0.51
    trans
    0.51
    POSITIVE LOGITS
    Пло
    0.55
    НИЕ
    0.55
    ник
    0.55
    '=>$
    0.54
     vivid
    0.54
     година
    0.52
     помочь
    0.52
    radioButton
    0.52
    istro
    0.52
    ാര്‍
    0.51
    Activations Density 0.006%

    No Known Activations