© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 538
    Prev
    Next
    INDEX
    Explanations

    Japanese

    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_44_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
     الطرف
    0.37
    TableViewCell
    0.35
     Peshawar
    0.34
    TrackedDevice
    0.34
    潛
    0.34
    痊
    0.33
    𝒾
    0.33
    Biological
    0.33
    峒
    0.33
    燬
    0.33
    POSITIVE LOGITS
     nk
    0.33
     kort
    0.33
     k
    0.31
     LA
    0.30
     n
    0.29
     Teknik
    0.29
     elekt
    0.29
     lũ
    0.29
     nahe
    0.29
    (
    0.29
    Activations Density 0.006%

    No Known Activations