© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5771
    Prev
    Next
    INDEX
    Explanations

    church or basilica

    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
     والط
    2.06
    kowe
    1.84
    >[</
    1.73
    шет
    1.70
    aceans
    1.67
    ۰
    1.64
    arkeit
    1.63
     îmb
    1.62
    estä
    1.61
     Согласно
    1.59
    POSITIVE LOGITS
     trato
    1.99
     lysosomes
    1.80
    おります
    1.77
     junctions
    1.76
     మంది
    1.73
    թ
    1.67
     jorn
    1.66
    gments
    1.64
     Calibri
    1.64
    days
    1.64
    Activations Density 0.001%

    No Known Activations