© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219036
    Prev
    Next
    INDEX
    Explanations

    around, surrounding, autour, вокруг

    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_31_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
    செ
    0.40
    alahan
    0.39
    သည်
    0.38
     राज्यात
    0.37
    delimiter
    0.37
    親
    0.36
     السلط
    0.36
    }+(\
    0.36
     کمپیوٹر
    0.36
    ಿಸ
    0.35
    POSITIVE LOGITS
     вокруг
    0.62
    围绕
    0.59
     Around
    0.55
     around
    0.54
     surrounding
    0.54
    Around
    0.54
     autour
    0.51
     ymp
    0.48
     attorno
    0.48
    Build
    0.47
    Activations Density 0.027%

    No Known Activations