© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4248
    Prev
    Next
    INDEX
    Explanations

    Kafka, streaming, AWS, Redpanda, Confluent

    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_39_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
     biliary
    0.38
     agentes
    0.36
     cortical
    0.36
    ("./
    0.34
    SPA
    0.34
     Biel
    0.34
     Bulb
    0.34
     agents
    0.34
    bele
    0.34
     Beh
    0.34
    POSITIVE LOGITS
    Leaves
    0.37
     öffentliche
    0.37
    Error
    0.37
    繋がりたい
    0.36
    acks
    0.35
     ইসলামিক
    0.35
     दिये
    0.35
    error
    0.34
    郆
    0.34
    partitions
    0.33
    Activations Density 0.002%

    No Known Activations