© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6307
    Prev
    Next
    INDEX
    Explanations

    ActiveMQ and message queues

    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_40_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
     împ
    0.41
    鼓
    0.38
    atr
    0.36
     drummer
    0.36
    Verm
    0.36
     Lip
    0.35
     verm
    0.35
    CB
    0.35
    肃
    0.35
    anel
    0.34
    POSITIVE LOGITS
     queues
    0.61
     Queue
    0.58
     queue
    0.55
     Que
    0.52
    Queue
    0.51
    Que
    0.46
    queue
    0.45
     Traf
    0.44
     queuing
    0.42
     evaluations
    0.41
    Activations Density 0.004%

    No Known Activations