© 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-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14381
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to formal reports and court proceedings or other official procedures

    oai_token-act-pair · gemini-2.0-flash

    opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.55
    ↵↵
    -0.51
    ']))
    -0.50
    <eos>
    -0.49
     "
    -0.48
     performance
    -0.47
    ])))
    -0.45
    /*++
    -0.44
    길
    -0.41
    ]))
    -0.41
    POSITIVE LOGITS
     kasarigan
    1.05
    AddTagHelper
    0.99
     leſs
    0.94
     myſelf
    0.94
     itſelf
    0.92
     pleaſure
    0.88
     purpoſe
    0.87
     bezeichneter
    0.86
     ſmall
    0.86
     Efq
    0.85
    Activations Density 29.065%

    No Known Activations