© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79337
    Prev
    Next
    INDEX
    Explanations

    Singapore places

    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_53_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
    غير
    0.44
     مذا
    0.42
    -])
    0.38
     보자
    0.38
     isim
    0.37
    ्रेड
    0.37
    轺
    0.37
     fred
    0.37
    oxyphenyl
    0.36
    邨
    0.36
    POSITIVE LOGITS
     nàng
    0.38
     preface
    0.38
    Tong
    0.37
    افه
    0.37
    انیہ
    0.36
     언
    0.36
     java
    0.35
     Cav
    0.35
     Br
    0.35
    Matt
    0.35
    Activations Density 0.001%

    No Known Activations