© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10691
    Prev
    Next
    INDEX
    Explanations

    `assertEqual` followed by programming libraries

    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_40_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
     گا۔
    0.45
     सक्
    0.43
     ofthe
    0.42
    ValueOf
    0.41
    lsulfanyl
    0.40
     አስተ
    0.39
     Wand
    0.39
     €,
    0.38
     स्थिरता
    0.38
     ':
    0.38
    POSITIVE LOGITS
    大约
    0.48
     plunging
    0.40
     PNP
    0.39
     tanpa
    0.38
     حوالي
    0.37
    hecy
    0.37
    Ꭾ
    0.36
     among
    0.36
     without
    0.35
     sekitar
    0.35
    Activations Density 0.000%

    No Known Activations