© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 219145
    Prev
    Next
    INDEX
    Explanations

    asylum seeker, vanadium, app, system

    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_16_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
     widening
    0.59
    내는
    0.57
     widened
    0.57
     widest
    0.57
     wide
    0.55
     deteriorated
    0.53
    اردوش
    0.53
     conspiring
    0.52
    轆
    0.52
     व्यापक
    0.52
    POSITIVE LOGITS
    ↵
    0.49
    a
    0.48
    our
    0.48
    Buying
    0.47
    an
    0.46
    K
    0.46
    ons
    0.46
    ;
    0.46
    able
    0.45
    Selective
    0.45
    Activations Density 0.000%

    No Known Activations