© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10621
    Prev
    Next
    INDEX
    Explanations

    municipalities and towns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     ////
    0.47
     hci
    0.47
     е
    0.46
     NIS
    0.46
    เกษ
    0.46
     biomass
    0.43
    е
    0.43
     р
    0.43
    Indigo
    0.43
    撹
    0.42
    POSITIVE LOGITS
     excelente
    0.59
    *
    0.56
     Bürgermeister
    0.49
    ificación
    0.47
    行
    0.47
     excellente
    0.46
     Excelente
    0.46
     solicitado
    0.45
    igueur
    0.45
    emailer
    0.44
    Activations Density 0.010%

    No Known Activations