© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46872
    Prev
    Next
    INDEX
    Explanations

    nihilism

    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_13_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
    v
    0.62
    {
    0.57
    iš
    0.53
    smtb
    0.51
    á
    0.50
    ó
    0.49
    cable
    0.49
    ishop
    0.49
    ..,
    0.49
    {//
    0.49
    POSITIVE LOGITS
     certeza
    0.52
     maîtrise
    0.50
    ייה
    0.50
     fractionation
    0.49
     robustness
    0.47
    َى
    0.47
     hiko
    0.46
     heavier
    0.46
     ricon
    0.46
    чества
    0.46
    Activations Density 0.000%

    No Known Activations