© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69423
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_46_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
    툐
    0.37
     പിന്നീട്
    0.35
     sensitization
    0.35
    휋
    0.34
    ϙ
    0.34
    قر
    0.34
    棕
    0.33
     निभाई
    0.33
    Maquina
    0.33
    랭
    0.33
    POSITIVE LOGITS
     thousands
    0.47
     milliers
    0.46
    Thousands
    0.44
     हजारों
    0.44
     Thousands
    0.43
    Tens
    0.41
    atakse
    0.37
    Addition
    0.37
     Kalk
    0.37
     Tens
    0.37
    Activations Density 0.020%

    No Known Activations