© 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-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229940
    Prev
    Next
    INDEX
    Explanations

    naturalism, naturalistic, intelligence

    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
    ми
    0.90
     час
    0.86
    もら
    0.84
    ლა
    0.84
     striis
    0.83
     dépassant
    0.83
    >(</
    0.81
    ،
    0.81
    را
    0.80
    mé
    0.80
    POSITIVE LOGITS
    ä
    1.31
    '
    1.12
    า
    1.10
    ada
    0.94
    um
    0.93
     Tema
    0.93
    s
    0.91
    รวม
    0.91
     Lis
    0.90
     Tarot
    0.88
    Activations Density 0.000%

    No Known Activations