© 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. 16525
    Prev
    Next
    INDEX
    Explanations

    python class methods and port definitions

    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
     సరి
    0.38
    ="|
    0.36
    apot
    0.36
    dating
    0.36
    expires
    0.35
    :\\
    0.35
     "@/
    0.34
    ଚ
    0.34
    ult
    0.33
    プラ
    0.33
    POSITIVE LOGITS
     لوبې
    0.40
    कर्णी
    0.39
     природных
    0.39
    akkhand
    0.39
     sixteen
    0.38
     żad
    0.38
    живання
    0.38
    ⑫
    0.38
    Catagory
    0.37
    Ỏ
    0.37
    Activations Density 0.003%

    No Known Activations