© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83161
    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_53_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
    assapi
    0.45
    드시
    0.42
    셋
    0.41
     Васи
    0.39
     camas
    0.38
    缺陷
    0.38
    መሳሳይ
    0.38
     Resmi
    0.38
     Jacinto
    0.37
    름
    0.37
    POSITIVE LOGITS
     geste
    0.39
    accommodation
    0.38
     Sar
    0.38
    飽
    0.38
    έν
    0.37
    Computational
    0.37
     Under
    0.36
    Sar
    0.36
    photon
    0.36
    internal
    0.36
    Activations Density 0.000%

    No Known Activations