© 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. 165917
    Prev
    Next
    INDEX
    Explanations

    a/an followed by a noun

    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
     around
    0.44
    送到
    0.41
    另一个
    0.40
     their
    0.39
     themselves
    0.39
     documenting
    0.38
     Teresa
    0.38
    >;
    0.34
    тров
    0.34
     美
    0.34
    POSITIVE LOGITS
     বাঁধা
    0.39
    辦
    0.39
     суще
    0.39
    ছেলে
    0.39
     bedeutet
    0.38
     измене
    0.37
    ्वती
    0.37
     హైద
    0.37
     असलेले
    0.37
     ფედერ
    0.37
    Activations Density 0.000%

    No Known Activations