© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193335
    Prev
    Next
    INDEX
    Explanations

    from X to Y

    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_27_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
     desped
    0.45
    皑
    0.44
     груп
    0.38
     conceivable
    0.36
     migrations
    0.36
    難
    0.36
     Pandora
    0.35
    Pooling
    0.35
     Konz
    0.35
     مارت
    0.35
    POSITIVE LOGITS
     LAD
    0.34
    녓
    0.33
    ନ୍ତି
    0.32
    verbosity
    0.32
    lett
    0.31
     শিক্ষ
    0.31
    ulaire
    0.31
     फिलहाल
    0.30
    harmed
    0.30
    ū
    0.30
    Activations Density 0.001%

    No Known Activations