© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44261
    Prev
    Next
    INDEX
    Explanations

    join clause or column

    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_3_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
    ৭
    0.56
    är
    0.55
    utional
    0.52
    య
    0.51
    กำหนด
    0.50
    的山
    0.50
    től
    0.50
    ้
    0.50
    ttino
    0.49
    kli
    0.49
    POSITIVE LOGITS
    join
    0.86
     join
    0.85
    joins
    0.80
    Join
    0.76
    のは
    0.74
     joins
    0.74
     życia
    0.73
     Join
    0.70
    ین
    0.70
     arquitectura
    0.70
    Activations Density 0.007%

    No Known Activations