© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125333
    Prev
    Next
    INDEX
    Explanations

    embouchure, breath, Sales

    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_37_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
     fatt
    0.39
    propagation
    0.38
    abar
    0.37
    fatt
    0.36
    $，
    0.36
    ppi
    0.36
    Читати
    0.35
    çı
    0.35
     previewBuilder
    0.35
    iega
    0.34
    POSITIVE LOGITS
     emboss
    0.40
    饴
    0.40
     Gold
    0.37
     intox
    0.37
     braces
    0.36
    ம்பு
    0.36
    HLIGHT
    0.36
    ждён
    0.36
     GOLD
    0.36
     embod
    0.36
    Activations Density 0.002%

    No Known Activations