© 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. 4896
    Prev
    Next
    INDEX
    Explanations

    Python class definitions

    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
    ך
    0.87
    িং
    0.83
     হ্যাঁ
    0.78
     circumference
    0.78
    л
    0.77
     Obec
    0.76
    ф
    0.75
     stencil
    0.74
    ➖➖
    0.73
    ancienne
    0.72
    POSITIVE LOGITS
    et
    0.84
    se
    0.83
    ll
    0.83
    в
    0.79
    ش
    0.74
    <bos>
    0.73
    с
    0.71
    Input
    0.69
    chol
    0.68
    思います
    0.67
    Activations Density 0.003%

    No Known Activations