© 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. 241308
    Prev
    Next
    INDEX
    Explanations

    Bash/Shell scripting

    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
     অবধি
    0.38
    stringProp
    0.37
    杷
    0.36
    িকারী
    0.35
    icron
    0.35
    ounced
    0.34
    軒
    0.34
    شانی
    0.34
    browserTarget
    0.33
    andha
    0.33
    POSITIVE LOGITS
     fout
    0.38
     الطعام
    0.38
    δια
    0.37
     التط
    0.37
     खाद
    0.36
     निरीक्षक
    0.35
    ANY
    0.35
     εφαρ
    0.35
    f
    0.35
    主义
    0.35
    Activations Density 0.001%

    No Known Activations