© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9188
    Prev
    Next
    INDEX
    Explanations

    sub

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     Contents
    0.66
     alternator
    0.64
     porttitor
    0.64
    เชิง
    0.64
    ielt
    0.63
    罅
    0.62
     Does
    0.62
    enei
    0.62
     Val
    0.62
     ਮੁ
    0.61
    POSITIVE LOGITS
     inspiring
    0.71
     समुच्चय
    0.69
     haunted
    0.67
     डिवा
    0.67
    estabelecimento
    0.66
     ಬ
    0.64
     провин
    0.63
    <unused1845>
    0.63
    ູ
    0.63
    <unused1051>
    0.61
    Activations Density 0.080%

    No Known Activations