© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180600
    Prev
    Next
    INDEX
    Explanations

    common prepositions and articles

    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_29_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
     wallets
    0.34
     শাল
    0.34
     repurchase
    0.33
    ფილი
    0.32
     ][
    0.32
     confesses
    0.32
    wallet
    0.32
     Dodson
    0.32
    ignées
    0.31
     دع
    0.31
    POSITIVE LOGITS
     Ά
    0.35
     الأخيرة
    0.34
    葯
    0.32
    聋
    0.31
     kwamba
    0.30
     ഞ
    0.30
     സംഭ
    0.30
    情況
    0.30
     Controls
    0.30
    flowing
    0.29
    Activations Density 0.008%

    No Known Activations