© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207020
    Prev
    Next
    INDEX
    Explanations

    surnames in context

    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_19_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
    迪
    0.39
    διά
    0.38
    Đi
    0.38
     isn
    0.36
    Η
    0.34
    之后
    0.34
    이어
    0.34
    제가
    0.34
    Dynam
    0.34
    Cort
    0.34
    POSITIVE LOGITS
    .:
    0.35
    .'
    0.34
     httpClient
    0.34
     Observer
    0.33
     титу
    0.32
    enem
    0.32
    engin
    0.32
     historiques
    0.31
     ننوت
    0.31
     enem
    0.31
    Activations Density 0.000%

    No Known Activations