© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 48
    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
    י
    0.34
    s
    0.30
     dictate
    0.29
    ാവ
    0.27
    ations
    0.27
    mals
    0.26
    िमी
    0.26
     خاطر
    0.26
    কিছু
    0.26
    عل
    0.25
    POSITIVE LOGITS
     razy
    0.31
    ى
    0.31
    OW
    0.29
    ب
    0.28
     opération
    0.28
     вариантов
    0.27
     స్థాయిలో
    0.27
    ʟ
    0.27
    pring
    0.26
    CAN
    0.26
    Activations Density 0.495%

    No Known Activations