© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38338
    Prev
    Next
    INDEX
    Explanations

    national assembly

    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_11_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
    ↵↵
    0.64
    ASON
    0.57
    s
    0.57
    0.56
    id
    0.55
     Sw
    0.55
    yn
    0.54
    ーズ
    0.54
    sd
    0.53
    pok
    0.53
    POSITIVE LOGITS
    我们
    0.68
     brillante
    0.64
    エラー
    0.64
     certamente
    0.63
     আমরা
    0.62
    iramente
    0.59
     ہوسک
    0.59
     errore
    0.59
    我們
    0.59
     terrib
    0.59
    Activations Density 0.000%

    No Known Activations