© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18872
    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_34_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
     Advis
    0.42
    Conditions
    0.34
     Instituto
    0.33
    Stored
    0.33
    疑問
    0.32
    ACES
    0.32
    蛸
    0.32
     வகை
    0.32
    Instituto
    0.32
     celebrated
    0.32
    POSITIVE LOGITS
     sudd
    0.43
     basin
    0.42
    ᶦ
    0.42
     sud
    0.41
     productId
    0.39
     soln
    0.38
     upstream
    0.37
    ကျင်
    0.37
     gfx
    0.37
     massless
    0.37
    Activations Density 0.000%

    No Known Activations