© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144463
    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_0_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
    0.53
    sele
    0.47
    rect
    0.47
     Less
    0.46
     Ses
    0.45
    timeout
    0.44
    <start_of_image>
    0.44
    ut
    0.44
    severe
    0.44
     Welfare
    0.44
    POSITIVE LOGITS
     energías
    0.70
    णार्‍या
    0.63
     nós
    0.62
    ⼈
    0.60
    
    0.59
     inmobili
    0.58
     ró
    0.57
    驄
    0.57
    نے
    0.56
    ᛁ
    0.56
    Activations Density 0.000%

    No Known Activations