© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230813
    Prev
    Next
    INDEX
    Explanations

    follow specific instructions or regulations

    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_6_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
    ৩
    1.17
    માં
    1.05
    ਰ
    1.02
    يا
    0.98
    t
    0.96
    es
    0.96
    ről
    0.95
    :
    0.95
    ER
    0.91
    ৪
    0.90
    POSITIVE LOGITS
     свобод
    0.91
     заседа
    0.89
     утеп
    0.83
     склон
    0.82
     приня
    0.81
    ق
    0.81
    ן
    0.81
     Enseñ
    0.78
     чувство
    0.78
     обеспечение
    0.77
    Activations Density 0.004%

    No Known Activations