© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48127
    Prev
    Next
    INDEX
    Explanations

    Based on the provided lists, especially the overwhelming presence of "ing" in `MAX_ACTIVATING_TOKENS` and the related terms like "warming" and tokens following "ing" such as "Technology", "capacity", "Temperatures", etc., the neuron seems to be related to ongoing processes or descriptions. The `TOP_POSITIVE_LOGITS` contain words like "regulation" and "hydration" which also fit this theme.A concise explanation would be:ongoing processes

    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_10_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
    t
    0.74
     frío
    0.74
     frio
    0.70
     dingin
    0.68
     cold
    0.68
     froide
    0.68
     hot
    0.66
     οποίο
    0.66
     públicos
    0.64
     fría
    0.64
    POSITIVE LOGITS
    след
    0.68
    zeitig
    0.66
     dispositivi
    0.65
    Have
    0.62
    regulation
    0.61
    hidrat
    0.61
     نے
    0.60
     Vegetables
    0.58
     उन्‍हें
    0.58
    czeniu
    0.57
    Activations Density 0.017%

    No Known Activations