© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227670
    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_6_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
    (
    1.05
    نا
    1.00
    يع
    0.96
    e
    0.86
    وع
    0.83
    لس
    0.79
    s
    0.77
    {
    0.77
    나
    0.77
    يك
    0.76
    POSITIVE LOGITS
     sobbing
    0.84
     reigning
    0.80
     billionaire
    0.79
    ı
    0.78
     この
    0.76
     crying
    0.73
     revamped
    0.73
     roaring
    0.72
     longing
    0.71
     desiderio
    0.71
    Activations Density 0.000%

    No Known Activations