© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121210
    Prev
    Next
    INDEX
    Explanations

    Cisco Quality of Service

    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_37_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
     уси
    0.36
    ラス
    0.36
    couvrez
    0.35
     конца
    0.34
     ডিভাই
    0.34
     FormGroup
    0.34
    ्रेसेस
    0.33
     እንቅስቃሴ
    0.33
    <iframe>
    0.33
    リーズ
    0.33
    POSITIVE LOGITS
     polyvinyl
    0.54
     electrocardi
    0.50
     interleukin
    0.49
     polyethylene
    0.45
     Escherichia
    0.45
     cannab
    0.43
     Jawaharlal
    0.40
     acrylonitrile
    0.40
     Bharatiya
    0.40
     ?,
    0.39
    Activations Density 0.401%

    No Known Activations