© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 209105
    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_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vidas
    0.39
     gotten
    0.38
    िलास
    0.37
    Ồ
    0.37
    ℎ
    0.37
     got
    0.37
     জাক
    0.37
     точке
    0.36
     شدند
    0.36
     schlecht
    0.36
    POSITIVE LOGITS
     För
    0.41
     Gipps
    0.40
     برای
    0.39
    För
    0.38
     для
    0.37
    Quant
    0.35
    cussions
    0.35
     барои
    0.34
     அலெ
    0.34
    媑
    0.34
    Activations Density 0.000%

    No Known Activations