© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54677
    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_31_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
     Joining
    0.41
     Before
    0.41
     ဖ
    0.38
    Before
    0.38
     体
    0.37
     Trab
    0.37
     अन्तर
    0.37
     ksi
    0.36
     Sporting
    0.36
     usuario
    0.36
    POSITIVE LOGITS
    스럽
    0.41
     ചെയ്യുന്ന
    0.37
     polypes
    0.37
     incrementally
    0.36
     Kiz
    0.36
    쾌
    0.36
    čaj
    0.36
     palpitations
    0.36
    ational
    0.35
     anesthet
    0.35
    Activations Density 0.000%

    No Known Activations