© 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. 3434
    Prev
    Next
    INDEX
    Explanations

    household cleaning activities

    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
    𝒊
    0.79
    𝒓
    0.76
    𝒖
    0.76
    𝒐
    0.74
    ェ
    0.71
    vtk
    0.68
    ट
    0.67
    \{
    0.66
     unmatched
    0.66
    டு
    0.65
    POSITIVE LOGITS
    𝑡
    0.79
    هما
    0.78
     capire
    0.78
    ا
    0.76
    滌
    0.76
    Laundry
    0.75
     laundry
    0.74
    𝑂
    0.74
     chodzi
    0.73
    𝑙
    0.73
    Activations Density 0.089%

    No Known Activations