© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19624
    Prev
    Next
    INDEX
    Explanations

    white rhinos

    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_15_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
     مث
    0.50
    ائ
    0.48
     ओ
    0.48
    گذ
    0.47
    شي
    0.47
     أق
    0.47
     مد
    0.46
    謝
    0.46
    AuthState
    0.46
    是
    0.45
    POSITIVE LOGITS
     stayed
    0.51
     contactless
    0.51
     sumptuous
    0.50
     delving
    0.50
     summing
    0.49
     summed
    0.49
     valuations
    0.48
     streaming
    0.48
     worms
    0.48
     enjoyed
    0.48
    Activations Density 0.000%

    No Known Activations