© 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. 57372
    Prev
    Next
    INDEX
    Explanations

    made

    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
     সেকেন্ড
    0.39
    Notas
    0.39
    r
    0.38
     الخامس
    0.38
    dr
    0.38
    t
    0.38
    ទី
    0.37
    Saludo
    0.37
    稼
    0.37
    我的
    0.37
    POSITIVE LOGITS
     From
    0.63
     under
    0.61
    From
    0.59
    under
    0.58
    FROM
    0.55
     Of
    0.53
     FROM
    0.52
     UNDER
    0.50
    Under
    0.50
    Of
    0.49
    Activations Density 0.001%

    No Known Activations