© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40729
    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_57_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
    ประมาณ
    0.38
    曺
    0.38
     আহম্মদ
    0.37
    ឡើង
    0.36
     amputation
    0.36
     f
    0.35
    ='"
    0.35
    alignParentRight
    0.35
     loudest
    0.35
     Amos
    0.34
    POSITIVE LOGITS
    ziff
    0.42
    縊
    0.40
    urra
    0.38
    仄
    0.38
     Nab
    0.37
     слад
    0.36
    iphone
    0.35
    asy
    0.35
    झे
    0.35
     যাই
    0.35
    Activations Density 0.000%

    No Known Activations