© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65095
    Prev
    Next
    INDEX
    Explanations

    bald

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     ante
    0.47
     ee
    0.42
    ral
    0.41
    eneo
    0.41
    ਾਈ
    0.40
     Combine
    0.40
    rees
    0.39
    爺
    0.39
    ee
    0.38
     Foy
    0.38
    POSITIVE LOGITS
    ुरु
    0.44
    ச்சு
    0.40
    काच्या
    0.39
     পুরুষ
    0.38
     कक्क
    0.38
    тился
    0.38
    ங்களிலிருந்து
    0.38
     кер
    0.37
     कर्क
    0.37
     कोलो
    0.36
    Activations Density 0.000%

    No Known Activations