© 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
    2. Gemma-3-27B-IT
    3. 32-GEMMASCOPE-2-TRANSCODER-262K
    4. 235094
    Prev
    Next
    INDEX
    Explanations

    B vitamins complex

    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_32_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
     weak
    0.39
    िसू
    0.39
     crowding
    0.38
    OECD
    0.38
    Protein
    0.38
    潤
    0.37
    Seth
    0.37
     Trib
    0.36
    润
    0.36
    OP
    0.36
    POSITIVE LOGITS
    ѧ
    0.40
     videoj
    0.39
    prints
    0.37
     일으
    0.37
    泷
    0.37
     ബാറ്ററി
    0.36
     BC
    0.35
    纪录
    0.35
    🌬
    0.35
    lemy
    0.35
    Activations Density 0.002%

    No Known Activations