© 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. 39811
    Prev
    Next
    INDEX
    Explanations

    pending orders

    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
    Negative Logits
    I
    0.71
    {
    0.67
    m
    0.64
    ↵
    0.62
    int
    0.62
    sl
    0.60
    lek
    0.58
     to
    0.57
    Whitespace
    0.57
     I
    0.56
    POSITIVE LOGITS
    Pend
    1.06
     pend
    0.96
     Pend
    0.94
    PEND
    0.86
     pendent
    0.83
    pend
    0.82
     pendiente
    0.80
     Pendleton
    0.78
     pendant
    0.73
    em
    0.71
    Activations Density 0.001%

    No Known Activations