© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164368
    Prev
    Next
    INDEX
    Explanations

    Levantine dialect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     '$(
    0.50
    ีก
    0.47
    تاجها
    0.47
     Trabaj
    0.45
    л
    0.44
     ምር
    0.44
    ى
    0.43
    虚
    0.43
     ጥቅ
    0.43
     hãy
    0.42
    POSITIVE LOGITS
    numbers
    0.61
    large
    0.58
    t
    0.56
    rums
    0.54
    lst
    0.52
    for
    0.51
    results
    0.51
    FOR
    0.51
    criminals
    0.51
    lips
    0.51
    Activations Density 0.000%

    No Known Activations