© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198709
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by determiners

    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_27_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
    ండో
    0.34
     Oreo
    0.33
    涩
    0.33
    uss
    0.32
    acknowledge
    0.32
    anything
    0.31
    ax
    0.31
     scratch
    0.31
    anath
    0.31
    satisfied
    0.31
    POSITIVE LOGITS
    Traditionally
    0.36
    Bloc
    0.36
    Кор
    0.35
     Після
    0.35
    Barcode
    0.35
    Ұ
    0.34
     Перед
    0.34
     تتم
    0.34
    ұ
    0.34
    Datab
    0.34
    Activations Density 0.000%

    No Known Activations