© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193274
    Prev
    Next
    INDEX
    Explanations

    describing characteristics

    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_9_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
     godina
    0.93
    يد
    0.87
     hodnot
    0.86
    ुल
    0.81
    3
    0.81
    রামর্শ
    0.80
     internationaux
    0.80
     lire
    0.78
     vrijed
    0.77
    পত্র
    0.76
    POSITIVE LOGITS
    t
    0.95
    an
    0.94
    ars
    0.91
    त
    0.89
    ेशन
    0.86
    น
    0.86
    </h3>
    0.85
    ี
    0.85
    ard
    0.80
     be
    0.79
    Activations Density 0.004%

    No Known Activations