© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 119
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ার্টমেন্ট
    1.06
     einzelnen
    0.96
    ${
    0.93
    ेटर
    0.87
     країн
    0.86
     señales
    0.85
    ährung
    0.82
     തന്നെ
    0.81
    لام
    0.81
    tok
    0.80
    POSITIVE LOGITS
    ע
    1.22
    𝑦
    1.10
    دوس
    1.02
     appetizer
    1.01
     traverses
    0.98
     costar
    0.98
    ſelf
    0.97
     storied
    0.96
    イド
    0.96
    ங்கிணை
    0.95
    Activations Density 0.616%

    No Known Activations