© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154057
    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_60_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
    discussion
    0.46
     Discussions
    0.46
     Reports
    0.45
     Nurses
    0.45
    Discussion
    0.43
    悰
    0.43
    了一個
    0.42
     Parents
    0.41
     Discussion
    0.41
    這裡
    0.41
    POSITIVE LOGITS
    '
    0.62
     observe
    0.60
     undertake
    0.54
     admire
    0.54
    ´
    0.52
     congratulate
    0.51
     check
    0.51
     recognize
    0.49
     rejoice
    0.49
     characterise
    0.48
    Activations Density 0.000%

    No Known Activations