© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217621
    Prev
    Next
    INDEX
    Explanations

    numbers and counting

    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_50_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
    १८६
    0.64
     ১৯৬৫
    0.63
     १८
    0.62
    十九
    0.61
    十七
    0.59
    ៦
    0.59
     пя
    0.58
    ৬৫
    0.57
    XVI
    0.57
     fifties
    0.55
    POSITIVE LOGITS
     பத்து
    0.53
     १०
    0.52
     दस
    0.52
     ten
    0.52
     eleven
    0.50
     eleventh
    0.50
     twelve
    0.50
     twelfth
    0.49
     Tenth
    0.48
     tenth
    0.47
    Activations Density 0.001%

    No Known Activations