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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 140437
    Prev
    Next
    INDEX
    Explanations

    say "the"

    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_46_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
    אס
    0.41
     正規品
    0.40
    뇨
    0.40
     भुला
    0.37
    ManagerProxy
    0.37
    ्यात
    0.35
    െടു
    0.35
    elez
    0.35
    鼗
    0.34
    най
    0.34
    POSITIVE LOGITS
    ória
    0.40
     VERS
    0.38
     tam
    0.38
     Season
    0.38
     свою
    0.38
     inexpensive
    0.38
     PRI
    0.38
     forms
    0.37
     Vers
    0.36
     determinants
    0.36
    Activations Density 0.001%

    No Known Activations