© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30448
    Prev
    Next
    INDEX
    Explanations

    broad strokes, city, church, exposure, research, sword

    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_10_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
    n
    0.69
     diminishing
    0.68
     dwindling
    0.67
     określ
    0.66
     menghasilkan
    0.64
     dangling
    0.61
    </h1>
    0.60
     pollutant
    0.60
     eradic
    0.60
     byproduct
    0.60
    POSITIVE LOGITS
    كر
    0.74
    সহ
    0.72
    స్
    0.71
    ží
    0.70
    كار
    0.70
    تي
    0.68
    قيم
    0.64
     acuerdos
    0.63
    4
    0.63
    كس
    0.62
    Activations Density 0.000%

    No Known Activations