© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111062
    Prev
    Next
    INDEX
    Explanations

    contamination 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_2_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
    ről
    0.96
    тей
    0.95
    beatCounter
    0.94
    ᱘
    0.93
    hesized
    0.87
    ίας
    0.85
    ﺪ
    0.82
    verständlich
    0.82
    ised
    0.81
     injuring
    0.80
    POSITIVE LOGITS
    ا
    2.03
    ق
    1.89
    م
    1.85
    ع
    1.78
    of
    1.77
    ف
    1.76
    W
    1.67
    د
    1.63
    un
    1.62
    ب
    1.60
    Activations Density 0.001%

    No Known Activations