© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172250
    Prev
    Next
    INDEX
    Explanations

    regex metacharacters

    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_20_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
    ሎ
    0.45
     parquet
    0.38
     법칙
    0.37
     ustawy
    0.36
     Instantiate
    0.36
    arrêté
    0.36
     promesa
    0.35
     marqué
    0.35
     universitario
    0.35
     gacch
    0.35
    POSITIVE LOGITS
     chewed
    0.48
    ttes
    0.45
    狷
    0.43
    પૂર્ણ
    0.43
     शिश
    0.41
     Abbreviations
    0.41
    chtigt
    0.41
    消耗
    0.41
    저
    0.40
    気
    0.40
    Activations Density 0.001%

    No Known Activations