© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225774
    Prev
    Next
    INDEX
    Explanations

    Taylor Swift

    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_10_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
    Д
    0.98
    م
    0.97
    غ
    0.96
    在
    0.90
    С
    0.87
    К
    0.86
    Т
    0.86
    Ε
    0.83
    В
    0.83
    У
    0.81
    POSITIVE LOGITS
    ordon
    0.72
    ón
    0.71
    óso
    0.70
     Gutiérrez
    0.69
    eské
    0.68
    ion
    0.67
    adio
    0.67
     possibilità
    0.66
    posto
    0.65
    apas
    0.65
    Activations Density 0.001%

    No Known Activations