© 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. 203851
    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
     ‌
    0.38
     '-')
    0.38
    ības
    0.36
     ""}
    0.35
     እን
    0.34
     મહિના
    0.34
    বস
    0.34
     Metern
    0.34
     WLR
    0.34
    ફ
    0.34
    POSITIVE LOGITS
    ลักษณ์
    0.38
    hosted
    0.37
    translational
    0.36
    नांक
    0.35
    ”
    0.35
     aimed
    0.35
     tasted
    0.34
     geared
    0.33
    SELS
    0.33
    OLS
    0.33
    Activations Density 0.000%

    No Known Activations