© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254080
    Prev
    Next
    INDEX
    Explanations

    1

    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_56_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
    тени
    0.37
    '}}
    0.36
    調
    0.36
    ข้อมูล
    0.35
    Gul
    0.34
    क़
    0.34
    اج
    0.33
    Razor
    0.33
     sixteen
    0.33
    WTO
    0.33
    POSITIVE LOGITS
     +
    0.61
     plus
    0.58
     Plus
    0.54
     плюс
    0.52
     PLUS
    0.52
     प्लस
    0.50
     +,
    0.50
     $+\
    0.49
     +\
    0.48
     플러스
    0.48
    Activations Density 0.000%

    No Known Activations