© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129500
    Prev
    Next
    INDEX
    Explanations

    Du

    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_50_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
     Noeud
    0.44
    ウェ
    0.40
    paysys
    0.39
    KK
    0.39
     웨
    0.38
     মাঠ
    0.37
    取得
    0.36
    টিক
    0.36
    ℕ
    0.36
    ReactNative
    0.36
    POSITIVE LOGITS
     ferries
    0.41
     ssd
    0.40
     Ferry
    0.39
    ssd
    0.39
    هش
    0.38
    סק
    0.38
    urov
    0.38
     ssl
    0.38
     fermentation
    0.37
     response
    0.37
    Activations Density 0.000%

    No Known Activations