© 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. 3096
    Prev
    Next
    INDEX
    Explanations

    XML schema properties

    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
    a
    0.85
    comer
    0.70
    ON
    0.70
    `${
    0.64
    one
    0.61
    t
    0.60
     असर
    0.58
    heap
    0.56
    ح
    0.56
    comers
    0.55
    POSITIVE LOGITS
     Dioxide
    0.74
    ी
    0.72
     Endowment
    0.72
    መሪያ
    0.68
    दी
    0.66
     amendment
    0.65
     Behold
    0.65
     circunstancias
    0.65
    motionProxy
    0.64
     rubbed
    0.64
    Activations Density 0.004%

    No Known Activations