© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170253
    Prev
    Next
    INDEX
    Explanations

    bringing the total number

    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_20_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
    Germany
    0.48
     filhos
    0.47
     Uzbekistan
    0.46
    Egypt
    0.46
    Ḫ
    0.44
    Ἀ
    0.44
    不想
    0.43
     Scholz
    0.43
    Wales
    0.43
     Aurang
    0.41
    POSITIVE LOGITS
     WAT
    0.42
     firepower
    0.42
    ags
    0.42
     firewall
    0.41
    EPA
    0.41
    ٩
    0.41
     كيف
    0.41
     wat
    0.40
     প্রচারিত
    0.39
     Firewall
    0.39
    Activations Density 0.000%

    No Known Activations