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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 228716
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     Wee
    0.41
    xx
    0.40
     outings
    0.38
     w
    0.37
     Le
    0.37
     Brittany
    0.36
     Mod
    0.36
     الأص
    0.36
     कब
    0.36
    oux
    0.36
    POSITIVE LOGITS
    回路
    0.40
     силы
    0.39
     রাক
    0.38
    hooter
    0.35
    スラ
    0.34
    ᆺ
    0.34
    cumulative
    0.34
    ழ்பெற்ற
    0.34
    صبحت
    0.33
    alanya
    0.33
    Activations Density 0.000%

    No Known Activations