© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51355
    Prev
    Next
    INDEX
    Explanations

    and therefore

    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
     returnPacket
    0.32
    ленной
    0.31
    Adjacent
    0.31
    翊
    0.30
     elucid
    0.29
    ления
    0.28
     удаления
    0.28
    📨
    0.28
     расту
    0.28
     usuario
    0.27
    POSITIVE LOGITS
     Oll
    0.33
    鐸
    0.33
     Okay
    0.32
     Papers
    0.32
     nd
    0.31
    robe
    0.30
     Unfortunately
    0.30
     Това
    0.30
    軻
    0.30
     ওর
    0.30
    Activations Density 0.002%

    No Known Activations