© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86271
    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_23_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
    ups
    0.46
     मोहब्बत
    0.45
     rule
    0.45
    ๑
    0.45
     Pisces
    0.44
    lying
    0.43
     ज़ि
    0.43
    s
    0.43
    rule
    0.42
     trouble
    0.41
    POSITIVE LOGITS
    را
    0.54
    ل
    0.54
    ق
    0.53
    وس
    0.51
    ير
    0.50
    ك
    0.50
    ر
    0.50
    פו
    0.48
    شب
    0.48
    フィ
    0.47
    Activations Density 0.000%

    No Known Activations