© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28782
    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_10_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
     gibt
    0.52
    大约
    0.51
     {
    0.50
    空
    0.49
    Έ
    0.49
    ना
    0.48
    Esta
    0.48
                      
    0.47
     aprile
    0.47
    POSITIVE LOGITS
    gger
    0.54
    nessy
    0.52
    ală
    0.51
    bergh
    0.51
     دهید
    0.50
     풍
    0.48
    nikov
    0.47
    fler
    0.47
    henburg
    0.47
    angan
    0.46
    Activations Density 0.000%

    No Known Activations