© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 129680
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     hereafter
    0.42
     excludes
    0.40
     ರಾಜ್ಯ
    0.39
    鷸
    0.39
    NANA
    0.38
     urls
    0.38
     refs
    0.38
     geolocation
    0.38
     nodules
    0.37
    ≣
    0.37
    POSITIVE LOGITS
    RO
    0.48
    ro
    0.40
    DE
    0.39
    वणे
    0.38
    ê
    0.38
    رو
    0.37
    Μ
    0.37
    LO
    0.37
    ிருந்தார்
    0.36
    RU
    0.36
    Activations Density 0.000%

    No Known Activations