© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197814
    Prev
    Next
    INDEX
    Explanations

    say ordinal suffixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     คร
    0.40
     ಸು
    0.40
    től
    0.40
     FCS
    0.39
    უშ
    0.38
     FSC
    0.38
     irmãos
    0.37
    ✷
    0.37
     prá
    0.37
     ​​​​
    0.36
    POSITIVE LOGITS
     Third
    0.55
    Third
    0.54
     third
    0.54
    third
    0.54
    III
    0.47
     dritten
    0.46
     III
    0.46
     derde
    0.44
     третий
    0.44
     треть
    0.43
    Activations Density 0.003%

    No Known Activations