© 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. 157766
    Prev
    Next
    INDEX
    Explanations

    foods and ingredients

    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
     محمود
    0.39
     Ngf
    0.38
    ungo
    0.38
    лад
    0.37
    Grilled
    0.37
    嘘
    0.37
     Recordemos
    0.37
    ्लाई
    0.36
     Guin
    0.36
    राज
    0.35
    POSITIVE LOGITS
     isomerization
    0.41
    泸
    0.40
    Legacy
    0.38
    瀘
    0.38
     venting
    0.37
    ެވެ
    0.37
    せん
    0.37
    BeanFactory
    0.36
     legacy
    0.36
    を実現
    0.36
    Activations Density 0.014%

    No Known Activations