© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214311
    Prev
    Next
    INDEX
    Explanations

    majority of

    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_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
    س
    1.92
    ס
    1.74
    تي
    1.58
    ט
    1.57
    ق
    1.45
    ত
    1.43
    स
    1.40
    ات
    1.39
    г
    1.38
    то
    1.37
    POSITIVE LOGITS
    for
    1.41
    liers
    0.99
    rij
    0.98
    lets
    0.98
    was
    0.98
    the
    0.96
    neath
    0.95
    क्षिप्त
    0.92
     Система
    0.91
    お店
    0.89
    Activations Density 0.001%

    No Known Activations