© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 80049
    Prev
    Next
    INDEX
    Explanations

    district

    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
     Midwest
    0.38
     tot
    0.38
     JI
    0.38
    抱
    0.37
    ющегося
    0.36
     Syn
    0.36
     imdb
    0.36
    ገድ
    0.35
     সমাধান
    0.35
    ⿳
    0.35
    POSITIVE LOGITS
    区
    1.45
    區
    1.34
    Qu
    1.27
    区的
    1.25
    qu
    1.24
     district
    1.19
     区
    1.19
    district
    1.16
     District
    1.16
    District
    1.14
    Activations Density 0.018%

    No Known Activations