© 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. 448
    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
     elapsed
    0.42
    մ
    0.37
    댓
    0.37
     abras
    0.36
    abras
    0.36
    при
    0.36
    껏
    0.36
     чином
    0.35
    artition
    0.35
     заве
    0.35
    POSITIVE LOGITS
    檚
    0.49
    
    0.48
     dull
    0.44
    야
    0.44
    ী
    0.44
    ৯
    0.43
    に
    0.43
     viewModel
    0.42
     dólares
    0.42
    𝑥
    0.42
    Activations Density 2.397%

    No Known Activations