© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12078
    Prev
    Next
    INDEX
    Explanations

    Descartes and dualism

    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
     закін
    0.56
     distribuzione
    0.55
    žky
    0.54
     spreader
    0.53
    lieben
    0.53
     diffuse
    0.52
     apricots
    0.52
    睉
    0.52
     dispersion
    0.52
    拡散
    0.52
    POSITIVE LOGITS
    С
    0.59
    ائ
    0.56
    И
    0.56
    Ни
    0.52
     С
    0.50
    igueur
    0.50
    )',
    0.49
    ﺎ
    0.49
    म्मद
    0.49
    *\
    0.48
    Activations Density 0.008%

    No Known Activations