© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140122
    Prev
    Next
    INDEX
    Explanations

    est

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    첫
    0.41
     Über
    0.38
     consistent
    0.38
    ฉ
    0.36
    σι
    0.35
     Lad
    0.35
    建模
    0.34
    Consistent
    0.34
    excited
    0.34
    Metaxy
    0.33
    POSITIVE LOGITS
    }"),
    0.40
    lerce
    0.40
     सुझा
    0.39
     congrats
    0.39
    ഞ്ഞ്
    0.39
    rative
    0.38
     ショ
    0.38
    下げ
    0.38
     Congrats
    0.38
     জানিয়ে
    0.38
    Activations Density 0.001%

    No Known Activations