© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 103120
    Prev
    Next
    INDEX
    Explanations

    regex special characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    浣
    0.43
    enta
    0.39
    şen
    0.38
    лян
    0.38
    álních
    0.37
     Quattro
    0.36
    नामा
    0.36
     sách
    0.36
    Great
    0.36
    ंति
    0.35
    POSITIVE LOGITS
    пли
    0.44
    licht
    0.40
    )]{
    0.38
     aroma
    0.37
     Healy
    0.37
     jed
    0.37
     hex
    0.37
     holl
    0.37
     xy
    0.36
    ."',
    0.36
    Activations Density 0.001%

    No Known Activations