© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194672
    Prev
    Next
    INDEX
    Explanations

    Israel and Israeli related

    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_9_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
    on
    0.34
    리티
    0.32
    сто
    0.31
    ご
    0.30
    人
    0.30
    xbox
    0.29
    x
    0.28
    port
    0.28
    ON
    0.28
    一番
    0.28
    POSITIVE LOGITS
     Israeli
    0.39
     Israel
    0.38
     arquitectura
    0.36
    以色列
    0.36
     Isra
    0.35
    ’
    0.34
    Israeli
    0.34
     Israelis
    0.34
     Yoga
    0.33
     Espresso
    0.33
    Activations Density 0.004%

    No Known Activations