© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 164776
    Prev
    Next
    INDEX
    Explanations

    symmetric or asymmetric concepts

    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_13_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
     Symmetry
    0.26
    symmetry
    0.23
    نی
    0.23
    дена
    0.21
    ली
    0.20
    iteit
    0.20
    اتی
    0.20
    디
    0.20
     symmetry
    0.19
    ده
    0.19
    POSITIVE LOGITS
     modalCard
    0.23
     व्हाउचर
    0.23
     Confucian
    0.23
     lymphatiques
    0.23
     对
    0.22
    OLYBD
    0.22
     معیار
    0.22
     येत
    0.21
     嗯
    0.21
     biosphere
    0.21
    Activations Density 0.004%

    No Known Activations