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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5616
    Prev
    Next
    INDEX
    Explanations

    The neuron detects the presence of "words" or "word" when followed by punctuation or formatting like closing parentheses, describing a word context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ु
    2.56
    𝙣
    2.42
    𝑦
    2.36
    ⽤
    2.34
    𝑜
    2.34
     hundred
    2.33
    𝑧
    2.32
    न्देल
    2.27
    多い
    2.26
    𝙖
    2.24
    POSITIVE LOGITS
    Ф
    2.54
     kanamycin
    2.49
    t
    2.45
    est
    2.42
    σεων
    2.40
     Biết
    2.39
    en
    2.38
    ं
    2.33
     NODE
    2.25
    LOADSTRING
    2.22
    Activations Density 0.129%

    No Known Activations