© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63877
    Prev
    Next
    INDEX
    Explanations

    Roman Empire

    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_46_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
    现代
    0.42
     modern
    0.41
     Modern
    0.37
    Modern
    0.37
     Byron
    0.37
    虔
    0.36
     bemo
    0.36
     Pines
    0.35
     lament
    0.35
     elevate
    0.35
    POSITIVE LOGITS
    するという
    0.42
     ಯಾವ
    0.38
     اسرائی
    0.38
    㚘
    0.38
    locationX
    0.37
    пру
    0.37
     مباشر
    0.37
    orduk
    0.36
     mundial
    0.36
    ʰ
    0.36
    Activations Density 0.007%

    No Known Activations