© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100104
    Prev
    Next
    INDEX
    Explanations

    21st century

    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_14_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
    heu
    0.54
     funkcji
    0.50
    Mip
    0.48
    р
    0.47
    i
    0.47
    难题
    0.47
    ك
    0.47
    st
    0.46
    HEP
    0.46
    ohyd
    0.46
    POSITIVE LOGITS
     cyclo
    0.55
     sæ
    0.54
     Selasa
    0.52
     lectores
    0.52
     generación
    0.52
    ücht
    0.50
     Fly
    0.50
     Kling
    0.50
     τους
    0.49
     Kwiatkowski
    0.49
    Activations Density 0.000%

    No Known Activations