© 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. 1462
    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
    و
    2.84
    т
    2.74
     Pradesh
    2.58
    ι
    2.57
    其
    2.55
    一个
    2.38
    以
    2.31
    onload
    2.29
    %).
    2.29
    า
    2.28
    POSITIVE LOGITS
    вання
    2.53
    siniz
    2.50
     envo
    2.43
     kelu
    2.43
    NSString
    2.41
    ন
    2.41
    عة
    2.40
    וד
    2.37
    
    2.33
    態
    2.33
    Activations Density 0.066%

    No Known Activations