© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81159
    Prev
    Next
    INDEX
    Explanations

    ger or Ger

    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_53_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
    ื่ม
    0.43
    锌
    0.40
     disampaikan
    0.37
    愔
    0.37
     صنع
    0.37
    ໕
    0.37
    eville
    0.36
    욌
    0.36
    ุม
    0.34
    安倍
    0.34
    POSITIVE LOGITS
     ger
    2.73
    Ger
    2.72
     Ger
    2.59
    ger
    2.50
    GER
    2.48
     GER
    2.36
     Gerald
    2.25
     Gerard
    2.23
    Gerald
    2.23
     Gerry
    1.97
    Activations Density 0.002%

    No Known Activations