© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64018
    Prev
    Next
    INDEX
    Explanations

    network pinging

    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_41_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
     Vla
    0.39
    Grouping
    0.38
     శా
    0.37
    ｵ
    0.36
    Кор
    0.36
     Carol
    0.36
    Ore
    0.35
    conditioning
    0.35
     তোলা
    0.35
     Carole
    0.35
    POSITIVE LOGITS
     ping
    2.08
     Ping
    1.93
    Ping
    1.89
    ping
    1.75
    PING
    1.41
     pong
    1.18
    乒
    1.11
    Pong
    1.10
     Pong
    1.09
    pong
    1.05
    Activations Density 0.001%

    No Known Activations