© 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
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157511
    Prev
    Next
    INDEX
    Explanations

    do

    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
    Not in Any Lists

    No Comments

    Negative Logits
    deh
    0.44
    Generating
    0.41
    zy
    0.41
    De
    0.40
    DE
    0.38
    obacterium
    0.38
     சுண்ணாம்பு
    0.38
    メ
    0.38
    jerne
    0.38
    bus
    0.38
    POSITIVE LOGITS
     nth
    0.39
     kth
    0.38
     spoiled
    0.37
     consensus
    0.36
     Eich
    0.36
     Thor
    0.36
    _{*
    0.35
     Diana
    0.35
     ninth
    0.35
     Monica
    0.35
    Activations Density 0.003%

    No Known Activations