© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99554
    Prev
    Next
    INDEX
    Explanations

    Vaadin Flow, Route, Wonders, developing economies

    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_16_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
    Parcel
    0.52
    Ⲥ
    0.51
     vorticity
    0.50
    ហ
    0.49
    sz
    0.48
    imately
    0.48
    🚑
    0.48
    ksz
    0.48
    Sz
    0.47
    wr
    0.47
    POSITIVE LOGITS
    ди
    0.54
    ный
    0.54
     dì
    0.49
    <0x8F>
    0.49
     GUN
    0.49
    <0x9B>
    0.48
     dedo
    0.48
     dibujar
    0.48
     deb
    0.47
     dir
    0.47
    Activations Density 0.000%

    No Known Activations