© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52961
    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_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
     deciduous
    0.40
     compartmental
    0.38
     await
    0.37
     compart
    0.37
     nuclei
    0.35
     compartment
    0.35
    潾
    0.35
    修士
    0.35
    Pero
    0.35
    Phir
    0.35
    POSITIVE LOGITS
    cor
    0.36
    fel
    0.35
    gev
    0.35
     étrangères
    0.35
     Deng
    0.33
    pect
    0.33
    cmd
    0.33
     সমস্ত
    0.33
    ijing
    0.33
     दर्
    0.33
    Activations Density 0.000%

    No Known Activations