© 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. 198014
    Prev
    Next
    INDEX
    Explanations

    function syntax

    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
     Beitrag
    0.39
    栗
    0.39
    ร่าง
    0.38
    Til
    0.38
    শ্য
    0.38
     Headline
    0.38
     মার
    0.37
    olutely
    0.36
     headline
    0.36
     CuO
    0.36
    POSITIVE LOGITS
     consumable
    0.44
     phd
    0.41
    aters
    0.39
    asse
    0.37
    orc
    0.36
    este
    0.36
    忻
    0.36
     recomm
    0.36
     Philly
    0.35
     pala
    0.34
    Activations Density 0.002%

    No Known Activations