© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2877
    Prev
    Next
    INDEX
    Explanations

    meat

    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_5_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
    k
    0.30
    يت
    0.30
     lucru
    0.29
    a
    0.29
    od
    0.29
    ا
    0.28
    𝒏
    0.28
    ot
    0.27
     earthquakes
    0.27
    ર્
    0.27
    POSITIVE LOGITS
    ＿
    0.34
    د
    0.34
    桕
    0.34
    𝑂
    0.33
     Pursuant
    0.33
     leyes
    0.33
    loaf
    0.33
    steak
    0.32
     PRP
    0.32
    வும்
    0.32
    Activations Density 0.062%

    No Known Activations