© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50536
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and programming errors

    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
    ທີ
    0.30
     calendario
    0.29
    entino
    0.29
    uut
    0.28
    Calendar
    0.28
     calendário
    0.28
    Concurrent
    0.27
    𝚇
    0.27
     считать
    0.26
    ᅴ
    0.26
    POSITIVE LOGITS
    즘
    0.25
     дя
    0.25
     saling
    0.25
    unicate
    0.25
     நடவடிக்கைகள்
    0.24
    arka
    0.24
     Él
    0.24
    arki
    0.24
    isting
    0.23
    aites
    0.23
    Activations Density 0.004%

    No Known Activations