© 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. 254221
    Prev
    Next
    INDEX
    Explanations

    long

    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
    是一些
    0.39
     싶
    0.36
    長的
    0.36
    អាច
    0.36
    都需要
    0.36
    既存
    0.36
    aparikkh
    0.36
    િસ
    0.35
     اسمبلی
    0.35
    싶
    0.35
    POSITIVE LOGITS
     viento
    0.54
     Previously
    0.50
     Wind
    0.48
     previously
    0.48
     wind
    0.47
     WIND
    0.47
     aa
    0.46
     terminal
    0.46
     ранее
    0.46
     Recently
    0.45
    Activations Density 0.000%

    No Known Activations