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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99413
    Prev
    Next
    INDEX
    Explanations

    Ingress Controller Nginx Traefik HAProxy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_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
     coastline
    0.65
     増
    0.52
     Soviet
    0.52
     증가
    0.52
     bookcase
    0.51
     demise
    0.50
     navy
    0.50
    ⦖
    0.49
     compatriots
    0.49
     각
    0.48
    POSITIVE LOGITS
    [
    0.59
     Child
    0.57
    ي
    0.54
    En
    0.52
    Child
    0.52
     Clusters
    0.51
     Hate
    0.51
    ટર
    0.50
    عند
    0.50
    тические
    0.50
    Activations Density 0.000%

    No Known Activations