© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89217
    Prev
    Next
    INDEX
    Explanations

    operational efficiency and impact

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.76
    ﻧ
    0.73
    ,
    0.64
     celebra
    0.64
     celebration
    0.61
    N
    0.60
     مدير
    0.59
    Celebrate
    0.59
     multipl
    0.58
     directeur
    0.58
    POSITIVE LOGITS
    ϵ
    0.59
     ของ
    0.57
     dė
    0.57
    োয়া
    0.55
    ęg
    0.54
    しみ
    0.54
    لیس
    0.53
     ले
    0.53
     금
    0.53
     noncommutative
    0.53
    Activations Density 0.001%

    No Known Activations