© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209852
    Prev
    Next
    INDEX
    Explanations

    Weimar Republic

    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_19_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
     රස
    0.45
     显示
    0.44
     टाइगर
    0.44
     ጉዳ
    0.42
     часы
    0.42
     ఇలా
    0.41
    鉚
    0.41
     bằng
    0.41
     וי
    0.40
     richtig
    0.40
    POSITIVE LOGITS
     apost
    0.43
     Horton
    0.41
    Esc
    0.41
    have
    0.40
     have
    0.39
    Erro
    0.39
     desec
    0.39
     away
    0.39
    Chand
    0.39
    ；
    0.39
    Activations Density 0.000%

    No Known Activations