© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17294
    Prev
    Next
    INDEX
    Explanations

    gerunds followed by nouns

    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
    Not in Any Lists

    No Comments

    Negative Logits
    power
    0.45
    cartes
    0.44
     power
    0.39
    ਕਾਰੀ
    0.39
     پیر
    0.39
     huis
    0.39
    策略
    0.38
    拼
    0.38
     Fris
    0.38
     strategia
    0.38
    POSITIVE LOGITS
     finance
    0.40
     Finance
    0.39
     danam
    0.38
     फाइनेंस
    0.38
     lauf
    0.38
    フィルタ
    0.38
     journalistic
    0.38
    하도록
    0.38
     बेटा
    0.37
    Finance
    0.37
    Activations Density 0.087%

    No Known Activations