© 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. 5688
    Prev
    Next
    INDEX
    Explanations

    codes with letters and numbers

    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
    ना
    0.89
    как
    0.88
     crave
    0.85
    assertEquals
    0.84
     fluctuations
    0.78
     contiguous
    0.77
    푞
    0.76
    ႉ
    0.76
    साइटी
    0.76
    峭
    0.76
    POSITIVE LOGITS
    ist
    0.99
    o
    0.97
    sustaining
    0.90
    sulph
    0.86
    sulf
    0.85
    zám
    0.85
    s
    0.85
    oğlu
    0.83
    ের
    0.83
    iktar
    0.83
    Activations Density 0.003%

    No Known Activations