© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37271
    Prev
    Next
    INDEX
    Explanations

    residency permits and citizenship

    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_11_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
    ።
    0.57
     ثاني
    0.47
     Cowboys
    0.46
    는
    0.46
    集團
    0.45
    ۔
    0.45
     confort
    0.45
    は
    0.45
    U
    0.45
     cowboys
    0.44
    POSITIVE LOGITS
    <0x80>
    0.54
     гражда
    0.46
    ？」
    0.44
    Converting
    0.44
    preserving
    0.44
     mempers
    0.43
    َس
    0.43
     inference
    0.43
    fing
    0.43
    an
    0.42
    Activations Density 0.061%

    No Known Activations