© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203904
    Prev
    Next
    INDEX
    Explanations

    fertilizing, fertilize

    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_6_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
    2
    0.91
    0.90
     anticoagulant
    0.88
    ้
    0.86
    ine
    0.84
     analgesic
    0.84
    ↵
    0.78
     at
    0.77
     subcutaneous
    0.77
    ่
    0.76
    POSITIVE LOGITS
    تي
    1.23
    مي
    1.18
     مي‌
    1.15
    وي
    1.14
    ي
    1.13
    s
    1.12
     مؤرشف
    1.11
    на
    1.09
    بير
    1.09
    ايا
    1.09
    Activations Density 0.000%

    No Known Activations