© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57367
    Prev
    Next
    INDEX
    Explanations

    third

    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_59_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
    ⑹
    0.39
    वले
    0.39
    6
    0.39
    izons
    0.38
    ikaze
    0.38
    lossen
    0.37
    тивы
    0.37
    រូប
    0.37
    inos
    0.37
    Gi
    0.37
    POSITIVE LOGITS
     Third
    0.66
     terceiro
    0.61
     tř
    0.58
     üçüncü
    0.57
     third
    0.57
     terceira
    0.57
     ③
    0.54
     तीसरा
    0.52
     மூன்ற
    0.52
     треть
    0.52
    Activations Density 0.004%

    No Known Activations