© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131886
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     छंद
    0.37
     ގ
    0.37
    engo
    0.36
    rtc
    0.36
     विद्रोह
    0.36
    <unused94>
    0.36
     Say
    0.36
    ান্ট
    0.35
     Revolt
    0.35
     gender
    0.35
    POSITIVE LOGITS
    Executive
    0.41
     Fif
    0.41
    Morgan
    0.40
     খু
    0.39
    Moscow
    0.39
    Ｍ
    0.39
    Tonel
    0.39
     diluted
    0.38
    asher
    0.38
    ]+\
    0.38
    Activations Density 0.000%

    No Known Activations