© 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. 165453
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    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
     येईल
    0.34
    сь
    0.33
     downside
    0.32
    >:
    0.32
    我
    0.32
     CEF
    0.31
     pall
    0.31
    呼び
    0.30
    ссию
    0.30
    筵
    0.30
    POSITIVE LOGITS
     ماذا
    0.39
     গর্ব
    0.37
    idCliente
    0.35
     Tw
    0.34
    市场上
    0.34
     प्रतिभाशाली
    0.34
    enumer
    0.34
    travel
    0.33
    zou
    0.33
     শহরে
    0.33
    Activations Density 0.007%

    No Known Activations