© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43855
    Prev
    Next
    INDEX
    Explanations

    AgGrid, Tech, integration, company

    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_3_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
    ﺭ
    0.76
     הח
    0.71
    ため
    0.70
    การ
    0.66
     הר
    0.66
     concret
    0.65
    Д
    0.64
     splinter
    0.63
    I
    0.63
     nende
    0.63
    POSITIVE LOGITS
    apest
    0.75
    vise
    0.71
    cemment
    0.66
    sentation
    0.66
    zott
    0.63
    leneck
    0.63
    )».
    0.62
    kih
    0.61
    ceased
    0.61
    erna
    0.57
    Activations Density 0.000%

    No Known Activations