© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174317
    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_20_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
     transm
    0.46
    提
    0.46
    机
    0.45
     doom
    0.43
    듦
    0.43
     distinctly
    0.42
    ริญ
    0.42
    什么是
    0.42
    機
    0.42
     substantial
    0.41
    POSITIVE LOGITS
    lassen
    0.50
    capacitor
    0.44
     vacaciones
    0.44
    ertas
    0.43
     ވަ
    0.42
    holen
    0.42
    soldiers
    0.41
     victimes
    0.41
    íticos
    0.41
    iteten
    0.41
    Activations Density 0.000%

    No Known Activations