© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222916
    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_10_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
     ]
    0.57
     )
    0.51
     ।
    0.49
     ttl
    0.47
    </em>
    0.46
     ],
    0.46
     ),
    0.44
    Elegant
    0.44
     '
    0.43
    Out
    0.43
    POSITIVE LOGITS
    Paulo
    0.52
     Morav
    0.50
    ल्ल्या
    0.50
    दास
    0.49
    ennes
    0.48
    ன்
    0.48
    ifact
    0.47
    ຢ
    0.47
    ellers
    0.46
    эх
    0.46
    Activations Density 0.000%

    No Known Activations