© 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. 14858
    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
     Five
    0.64
    五
    0.63
     Four
    0.62
    FIVE
    0.59
    Four
    0.58
     FIVE
    0.55
    四
    0.55
     four
    0.54
    Five
    0.54
     пя
    0.54
    POSITIVE LOGITS
     nine
    0.96
    nine
    0.87
     девя
    0.83
     nueve
    0.77
     eight
    0.77
    九
    0.77
    Nine
    0.77
     neun
    0.76
     Nine
    0.75
    eight
    0.75
    Activations Density 0.059%

    No Known Activations