© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88640
    Prev
    Next
    INDEX
    Explanations

    children

    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_60_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
     tử
    0.37
    𒅗
    0.36
    ▢
    0.36
    ciu
    0.34
    ̣
    0.34
     باب
    0.34
    ził
    0.34
    丷
    0.33
     एग्जाम्स
    0.32
    ńczy
    0.32
    POSITIVE LOGITS
     children
    3.75
    Children
    3.56
     Children
    3.55
    children
    3.52
     CHILDREN
    3.19
     kinderen
    3.00
     детей
    2.94
     बच्चों
    2.84
     childrens
    2.77
     dzieci
    2.72
    Activations Density 0.000%

    No Known Activations