© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5553
    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_40_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
    uat
    0.49
    новения
    0.41
     шанс
    0.41
     বছর
    0.39
     readership
    0.38
     Nakam
    0.38
    牌
    0.38
     predators
    0.37
    냠
    0.37
     terus
    0.36
    POSITIVE LOGITS
     foot
    0.91
    Foot
    0.91
     Foot
    0.88
    foot
    0.86
    FOOT
    0.77
     footer
    0.75
     FOOT
    0.74
    footer
    0.72
     Footer
    0.71
     voet
    0.70
    Activations Density 0.001%

    No Known Activations