© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145642
    Prev
    Next
    INDEX
    Explanations

    common/proper

    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_59_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
    כ
    1.25
     בכ
    1.20
     לכ
    1.19
     הכ
    0.79
     וכ
    0.78
     מכ
    0.76
    כר
    0.72
    וכ
    0.64
    כב
    0.62
     gentle
    0.58
    POSITIVE LOGITS
     common
    0.48
     bonus
    0.46
     común
    0.41
     Common
    0.41
     कॉमन
    0.40
    árez
    0.37
    cury
    0.37
     Hib
    0.37
     মূলত
    0.36
     proper
    0.36
    Activations Density 0.000%

    No Known Activations