© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36853
    Prev
    Next
    INDEX
    Explanations

    uhaul pick, U-2 reconnaissance, U-NET GAN, U-2 Incident, U-20 World Cup, Uranium-235

    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_3_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
    ید
    0.75
    ες
    0.69
     pudd
    0.69
    ת
    0.68
    mainan
    0.68
    𝗱
    0.68
    کم
    0.66
    듑
    0.65
     دیں۔
    0.65
    وٹی
    0.64
    POSITIVE LOGITS
     I
    1.02
     was
    0.97
    1
    0.77
    I
    0.77
     S
    0.75
     of
    0.73
    Instruction
    0.72
     for
    0.71
    i
    0.70
    All
    0.70
    Activations Density 0.005%

    No Known Activations