© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5661
    Prev
    Next
    INDEX
    Explanations

    file descriptor system calls

    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_39_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
    RegisterClass
    0.41
     رج
    0.37
    threads
    0.37
    вига
    0.37
     Carmichael
    0.36
    🧵
    0.36
    rmi
    0.35
     minimising
    0.35
     குற
    0.34
    सोल
    0.34
    POSITIVE LOGITS
     Einstein
    0.42
     Brookhaven
    0.40
    ierten
    0.38
    юн
    0.37
     Sponsored
    0.37
    дие
    0.37
     Marcell
    0.37
    蝙
    0.37
     Jacobs
    0.36
    bius
    0.36
    Activations Density 0.026%

    No Known Activations