© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1469
    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
     pens
    1.49
    ین
    1.47
     dolayı
    1.44
    ра
    1.41
    筆
    1.35
    ishes
    1.33
    ятся
    1.30
    """.
    1.30
    ଚ
    1.30
    ın
    1.28
    POSITIVE LOGITS
    एं
    1.76
    ction
    1.68
    т
    1.52
     engulf
    1.50
    c
    1.49
     annihil
    1.47
    ➢
    1.43
     previsto
    1.37
    ओ
    1.37
    ว์
    1.32
    Activations Density 0.108%

    No Known Activations