© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49838
    Prev
    Next
    INDEX
    Explanations

    Latin Quarter, Latin America

    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_10_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
    v
    0.35
    ä
    0.33
    n
    0.32
    l
    0.30
    f
    0.29
    ali
    0.28
    lin
    0.26
    c
    0.25
     is
    0.25
    m
    0.25
    POSITIVE LOGITS
    パイ
    0.23
     chadd
    0.23
    プラグ
    0.21
     aplica
    0.20
    ходил
    0.20
    Фа
    0.20
    ップ
    0.19
    انات
    0.19
    ור
    0.19
     quedan
    0.19
    Activations Density 0.004%

    No Known Activations