© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96293
    Prev
    Next
    INDEX
    Explanations

    protected $table

    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_14_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
    udy
    0.53
    closures
    0.50
    soluble
    0.50
    ée
    0.49
    amen
    0.48
    user
    0.48
    threaded
    0.48
    ap
    0.48
    ہا
    0.47
     );
    0.47
    POSITIVE LOGITS
     motorcycl
    0.60
    微微
    0.55
     motorbike
    0.54
     βασ
    0.54
     మండల
    0.53
     എന്നാല്‍
    0.51
     imasmim
    0.51
     vigilant
    0.51
    紫外
    0.51
     Natürlich
    0.51
    Activations Density 0.000%

    No Known Activations