© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9770
    Prev
    Next
    INDEX
    Explanations

    London

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    santa
    0.70
    松
    0.66
     शिवसेना
    0.66
     ГӀ
    0.66
     जाट
    0.65
     Duluth
    0.65
    Ou
    0.64
     Sinal
    0.64
     松
    0.63
     Shibata
    0.62
    POSITIVE LOGITS
     London
    1.44
     لندن
    1.39
    伦敦
    1.32
    London
    1.30
     Londra
    1.28
     london
    1.26
     Londres
    1.20
     Lond
    1.19
     Oxford
    1.16
     लंदन
    1.14
    Activations Density 0.138%

    No Known Activations