© 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. 196647
    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
     相
    0.41
    endas
    0.39
     Cocker
    0.38
     summa
    0.38
    Ϝ
    0.37
    بو
    0.36
     लोहा
    0.36
     Turbulence
    0.36
    zar
    0.36
    geries
    0.36
    POSITIVE LOGITS
    >**
    0.39
     rak
    0.37
    oki
    0.37
    OY
    0.36
     gaskets
    0.36
     coy
    0.36
     뛰
    0.36
     Jit
    0.36
    сторія
    0.35
     Dell
    0.35
    Activations Density 0.000%

    No Known Activations