© 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. 23950
    Prev
    Next
    INDEX
    Explanations

    guidance

    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
    ↵
    0.73
    k
    0.70
     periode
    0.69
     ponytail
    0.69
     entourage
    0.67
     aerospace
    0.65
    ми
    0.65
     Vegas
    0.64
    汅
    0.64
     propre
    0.64
    POSITIVE LOGITS
    К
    0.94
    {
    0.92
    “
    0.88
    Се
    0.77
    Об
    0.76
    (“
    0.76
    П
    0.75
    С
    0.75
    Т
    0.73
    Про
    0.73
    Activations Density 0.000%

    No Known Activations