© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247353
    Prev
    Next
    INDEX
    Explanations

    disk partitions like sda1

    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_40_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
    感兴趣
    0.39
     incred
    0.38
     impressive
    0.37
     decreasing
    0.37
    îte
    0.37
     aspects
    0.36
    磊
    0.36
     TCE
    0.35
     Mul
    0.35
     impressively
    0.35
    POSITIVE LOGITS
     пога
    0.44
     harbors
    0.43
    ন্দন
    0.39
    劉
    0.39
     antennis
    0.37
     harbor
    0.37
     Harbor
    0.37
     harbours
    0.36
    ণিত
    0.36
    Lng
    0.36
    Activations Density 0.002%

    No Known Activations