© 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. 67834
    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
     onSuccess
    0.39
    )\
    0.37
     politic
    0.36
    اوى
    0.36
    letter
    0.36
    smouth
    0.35
    );\
    0.35
    )}\
    0.35
     Tinggi
    0.34
    égi
    0.34
    POSITIVE LOGITS
    Detailed
    0.61
    Save
    0.59
     detailed
    0.58
    Saving
    0.57
     बचाने
    0.57
     saves
    0.56
     Detailed
    0.56
     saving
    0.55
    saves
    0.54
     saved
    0.54
    Activations Density 0.000%

    No Known Activations