© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213074
    Prev
    Next
    INDEX
    Explanations

    authors and researchers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     रंजन
    0.44
    Harry
    0.40
     हेनरी
    0.39
    modify
    0.38
     Henrik
    0.38
    ಳಿತ
    0.37
     compless
    0.37
    槇
    0.37
     सिलेक्शन
    0.36
    Kenneth
    0.36
    POSITIVE LOGITS
    溦
    0.43
    MktCap
    0.40
    وش
    0.39
     Sarg
    0.39
    वाट
    0.39
    LOUISE
    0.38
     waf
    0.38
     Wadd
    0.38
    চো
    0.37
    asha
    0.37
    Activations Density 0.000%

    No Known Activations