© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35478
    Prev
    Next
    INDEX
    Explanations

    particles enter bloodstream

    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_31_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
    合わせ
    0.39
    弦
    0.37
     padding
    0.37
     provision
    0.36
     source
    0.36
     client
    0.36
    帕
    0.35
     small
    0.34
     solution
    0.34
    ستر
    0.34
    POSITIVE LOGITS
    čnosti
    0.46
    কেশন
    0.44
    носи
    0.41
    мень
    0.40
    jne
    0.39
     sót
    0.39
     LANE
    0.39
    叓
    0.38
    ্ের
    0.38
     রিটার
    0.38
    Activations Density 0.004%

    No Known Activations