© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147017
    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_18_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
    ↵↵
    0.87
    t
    0.78
    ↵
    0.61
      
    0.61
    f
    0.61
    b
    0.59
    st
    0.59
    the
    0.59
     ,
    0.58
     What
    0.57
    POSITIVE LOGITS
     introns
    0.55
     drugih
    0.54
    beatCounter
    0.51
    各项
    0.49
     Monika
    0.49
    𝗈
    0.49
     Verenig
    0.48
    𝕂
    0.48
    ţiei
    0.48
    ênd
    0.48
    Activations Density 0.000%

    No Known Activations