© 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. 813
    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
    カイブ
    2.59
    ЕТ
    2.43
    ول
    2.13
    ئيس
    2.04
    ף
    2.03
    ,{\
    2.02
    ographers
    2.00
     kitchens
    1.99
    зывают
    1.99
     βρί
    1.97
    POSITIVE LOGITS
    ം
    3.05
    ください
    2.69
    ة
    2.40
    ки
    2.35
    at
    2.25
     pareil
    2.24
    i
    2.22
     ulter
    2.21
     sobra
    2.21
    a
    2.17
    Activations Density 0.081%

    No Known Activations