© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 157933
    Prev
    Next
    INDEX
    Explanations

    gold

    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
    \|_{\
    0.38
     cucina
    0.38
    unat
    0.37
     국내
    0.36
     terci
    0.36
     warning
    0.35
    🚚
    0.35
    廚
    0.35
     Junio
    0.34
    otechn
    0.34
    POSITIVE LOGITS
     золо
    0.44
    Golden
    0.41
    金
    0.41
     KE
    0.40
    Power
    0.40
    gold
    0.39
    Gold
    0.38
    ServiceProvider
    0.38
    GOLD
    0.38
     Golden
    0.37
    Activations Density 0.001%

    No Known Activations