© 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. 24884
    Prev
    Next
    INDEX
    Explanations

    I

    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
    Seller
    0.52
     seller
    0.50
     Seller
    0.49
     kolay
    0.46
    easy
    0.46
    易
    0.46
    容易
    0.45
    簡単
    0.44
     easy
    0.43
     facilmente
    0.43
    POSITIVE LOGITS
    cussions
    0.38
     welcome
    0.38
    bari
    0.37
     share
    0.37
    Ｑ
    0.36
     Need
    0.36
     cần
    0.36
     необхідно
    0.36
    ຕ້ອງການ
    0.35
     strike
    0.35
    Activations Density 0.002%

    No Known Activations