© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 48664
    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
     Treatments
    0.49
     Creativity
    0.49
    ргани
    0.49
    thebetter
    0.48
    >\<^
    0.47
     പ്രസി
    0.47
     Milner
    0.47
     Schemes
    0.46
     चुने
    0.45
     Mön
    0.45
    POSITIVE LOGITS
     vara
    0.49
     unen
    0.46
    aret
    0.44
    ROC
    0.44
     obligatory
    0.43
     sail
    0.43
    omin
    0.42
    RO
    0.41
     nig
    0.41
    坎
    0.41
    Activations Density 0.000%

    No Known Activations