© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19687
    Prev
    Next
    INDEX
    Explanations

    comparison of weight

    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_15_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
     przys
    0.54
     fromi
    0.53
     missione
    0.53
    无人
    0.52
     pendientes
    0.50
     ткани
    0.50
     bequeathed
    0.50
     conhecimentos
    0.50
     firearms
    0.49
    壽
    0.49
    POSITIVE LOGITS
    Video
    0.61
     مارس
    0.53
    קד
    0.50
    Climate
    0.49
    Fluid
    0.49
    Harvard
    0.48
    народ
    0.47
    ە
    0.47
     ر
    0.47
    encoding
    0.47
    Activations Density 0.003%

    No Known Activations