© 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. 131381
    Prev
    Next
    INDEX
    Explanations

    Al-Raune, Caesar salad, Kaiser Permanente

    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
    리
    1.41
    د
    1.22
    م
    1.14
    р
    1.08
    ص
    1.05
    ک
    1.03
    v
    1.02
    ր
    1.02
    ف
    1.01
    ड
    0.99
    POSITIVE LOGITS
     pomocí
    0.98
     ajutor
    0.98
     medizin
    0.96
     přes
    0.95
     těch
    0.95
     κατά
    0.93
     nij
    0.93
     يب
    0.93
     není
    0.93
    <0xF3>
    0.91
    Activations Density 0.000%

    No Known Activations