© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51916
    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_30_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
     harmon
    0.40
    :";
    0.40
     veste
    0.40
     &,
    0.38
     ऑर्डर
    0.38
     wills
    0.38
     rbind
    0.38
     order
    0.37
     भाग
    0.36
     volte
    0.36
    POSITIVE LOGITS
     rửa
    0.39
    లిన
    0.38
    ^{*
    0.38
    Chronic
    0.37
     nosotros
    0.36
     সৃষ্ট
    0.36
    wilderness
    0.35
     bitumen
    0.34
    кугӀ
    0.34
    ವುದು
    0.34
    Activations Density 0.000%

    No Known Activations