© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49684
    Prev
    Next
    INDEX
    Explanations

    tea and festive treats

    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_55_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
     टर्म
    0.42
    ሊ
    0.37
    టన
    0.37
     Term
    0.35
    Term
    0.35
    อะ
    0.35
    優秀
    0.35
    ުގައި
    0.34
    ارم
    0.34
    Terminology
    0.34
    POSITIVE LOGITS
     impresses
    0.43
     厚
    0.40
    methylsulfanyl
    0.40
    厚
    0.39
     healthy
    0.39
     tr
    0.38
     impressed
    0.38
     impres
    0.37
     помі
    0.37
     हेल्दी
    0.37
    Activations Density 0.016%

    No Known Activations