© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89055
    Prev
    Next
    INDEX
    Explanations

    Modern Standard Arabic and Warfare

    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_3_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
     in
    0.75
    ING
    0.70
     of
    0.68
     आरोपी
    0.68
    ق
    0.66
    ).”
    0.64
    kia
    0.59
     Благодаря
    0.59
     في
    0.58
    elyn
    0.57
    POSITIVE LOGITS
    ر
    0.65
    籾
    0.61
    n
    0.59
    ustion
    0.58
    谓
    0.57
    دهای
    0.56
    См
    0.56
    t
    0.56
     Sonn
    0.55
    spě
    0.55
    Activations Density 0.007%

    No Known Activations