© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87123
    Prev
    Next
    INDEX
    Explanations

    single atom catalysis

    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_23_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
    {
    0.41
    तिक
    0.41
    optional
    0.39
     Utilization
    0.39
     Utilizing
    0.39
    yout
    0.38
     Mixtures
    0.38
     Environment
    0.38
     compensating
    0.38
     tia
    0.38
    POSITIVE LOGITS
    🜨
    0.43
     amante
    0.41
     amantes
    0.39
     রোগে
    0.38
     choroby
    0.37
     tàu
    0.36
     giãn
    0.36
    苹果
    0.35
     çünkü
    0.35
    ᆫ
    0.35
    Activations Density 0.003%

    No Known Activations