© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117442
    Prev
    Next
    INDEX
    Explanations

    run go work Data electrical

    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_27_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
     často
    0.35
     often
    0.34
     folio
    0.34
     dozens
    0.33
    often
    0.33
    abatic
    0.33
    だったので
    0.32
    ش
    0.32
     Spring
    0.32
     ი
    0.32
    POSITIVE LOGITS
     greatness
    0.38
    之处
    0.37
     ट्वी
    0.36
    ้อน
    0.35
     परिस्थिति
    0.35
     পরিপ্রে
    0.35
    แต่
    0.34
     парни
    0.34
    𝘋
    0.34
     пунк
    0.34
    Activations Density 0.001%

    No Known Activations