© 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
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 259635
    Prev
    Next
    INDEX
    Explanations

    Adidas, Nike, Vans, New Balance, Converse, Chuck Taylor, Authentic, Old Skool, React Infinity

    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_22_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
    به
    0.26
    न्त
    0.25
     fools
    0.24
    Bearing
    0.23
    Rep
    0.23
    Scope
    0.23
    婊
    0.22
     vows
    0.22
    ラブ
    0.22
    Nim
    0.21
    POSITIVE LOGITS
     Fiscalía
    0.27
     aldrig
    0.27
     ઉમે
    0.27
     ២
    0.26
    டையாக
    0.26
     '');
    0.25
    他にも
    0.25
     predicate
    0.25
     pedra
    0.25
     ×
    0.25
    Activations Density 0.001%

    No Known Activations