© 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. 1396
    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
    𝐧
    3.23
    𝐩
    3.11
    𝐞
    2.89
    𝐝
    2.87
    stackrel
    2.85
    اس
    2.84
    𝐦
    2.74
    𝐫
    2.73
    𝐨
    2.72
    𝐢
    2.69
    POSITIVE LOGITS
    ப்படி
    2.74
    ஔ
    2.68
    '/
    2.64
     похађа
    2.57
    establishment
    2.55
    l
    2.51
    
    2.48
    lop
    2.45
    userInfo
    2.44
     namanya
    2.44
    Activations Density 0.057%

    No Known Activations