© 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. 215733
    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
    码
    0.45
    kar
    0.41
     Omar
    0.40
    maya
    0.39
    Tek
    0.39
    Corp
    0.39
    май
    0.39
    inales
    0.39
    kV
    0.38
     Tek
    0.38
    POSITIVE LOGITS
     dźwię
    0.43
    ]".
    0.40
     photosphere
    0.38
     সম্পূর্ণরূপে
    0.38
     çiçek
    0.37
     mandible
    0.37
     heavens
    0.36
     bunyi
    0.36
    茧
    0.36
     Psychiatric
    0.36
    Activations Density 0.000%

    No Known Activations