© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235775
    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_46_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
    厛
    0.43
    的影响
    0.43
     situazioni
    0.40
    影響
    0.40
    ◡
    0.39
    夏季
    0.38
    の影響
    0.37
    嶷
    0.37
    र्ख
    0.37
     föld
    0.37
    POSITIVE LOGITS
    \\"
    0.39
    CHE
    0.39
    Sah
    0.39
    prung
    0.38
     असे
    0.38
    rency
    0.37
     Outside
    0.37
     шпа
    0.37
    portion
    0.36
    rise
    0.35
    Activations Density 0.000%

    No Known Activations