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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173493
    Prev
    Next
    INDEX
    Explanations

    especially, especially when

    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
    Not in Any Lists

    No Comments

    Negative Logits
    iaz
    0.37
     Douglas
    0.37
    adou
    0.34
     $\
    0.34
     Would
    0.34
     \
    0.34
     pn
    0.34
    azen
    0.33
     La
    0.33
    db
    0.33
    POSITIVE LOGITS
    বৃদ্ধি
    0.35
     ближе
    0.35
     ataques
    0.34
     tulaj
    0.34
    绝
    0.34
    炅
    0.34
    ശ
    0.34
     stärker
    0.34
     hỗn
    0.34
    販
    0.33
    Activations Density 0.006%

    No Known Activations