© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178051
    Prev
    Next
    INDEX
    Explanations

    cybersecurity, threat detection

    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_50_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
    ーム
    0.41
    Mé
    0.41
    Realm
    0.39
    AIR
    0.39
     пала
    0.39
     TBR
    0.38
    RelativeLayout
    0.38
    럭
    0.38
    tencent
    0.38
    лка
    0.37
    POSITIVE LOGITS
     onay
    0.42
    สเตอร์
    0.40
     Cyprus
    0.39
     zvý
    0.38
     đặt
    0.38
    ভাত
    0.37
     FEI
    0.37
     Kun
    0.37
     urge
    0.37
     Cyl
    0.36
    Activations Density 0.001%

    No Known Activations