© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 31187
    Prev
    Next
    INDEX
    Explanations

    Looking at the provided lists:- `MAX_ACTIVATING_TOKENS` is dominated by `getElementById`.- `TOKENS_AFTER_MAX_ACTIVATING_TOKEN` shows that `getElementById` is consistently followed by `(`.This strongly suggests the neuron is related to JavaScript code, specifically the `document.getElementById` function call. The `TOP_POSITIVE_LOGITS` list is a distraction or noise in this case, as the other lists provide a clear and specific pattern.Therefore, a concise explanation would focus on the `getElementById` sequence.`document.getElementById(`document.getElementById

    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
    馳
    0.41
    Artikel
    0.39
    ቸው
    0.39
    OpenCamera
    0.38
    𝜁
    0.38
    iential
    0.38
    artikel
    0.37
    ტიკ
    0.36
    ioctl
    0.36
     Wheaton
    0.36
    POSITIVE LOGITS
     सुविधाओं
    0.39
     मंगल
    0.38
    rase
    0.38
     Shat
    0.36
     ORDIN
    0.36
     Bla
    0.36
     afet
    0.35
     fatalities
    0.35
     высоких
    0.35
    偪
    0.35
    Activations Density 0.000%

    No Known Activations