© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197059
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
    Critics
    0.62
    Liam
    0.49
    Growth
    0.48
    Mem
    0.47
    Men
    0.47
    Gaming
    0.46
    和谐
    0.46
    倍
    0.46
    Training
    0.46
    并且
    0.46
    POSITIVE LOGITS
     washes
    0.54
     welds
    0.51
     knocks
    0.50
    ᇂ
    0.50
     kinks
    0.49
     어디
    0.48
    螂
    0.48
     sails
    0.47
     td
    0.47
     월
    0.46
    Activations Density 0.000%

    No Known Activations