© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8187
    Prev
    Next
    INDEX
    Explanations

    research-oriented language about scientific results

    oai_token-act-pair · gemini-2.0-flash

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     CreateTagHelper
    -1.12
     كومونز
    -0.90
     MainAxisSize
    -0.85
    ंदीखरीदारी
    -0.79
    abestanden
    -0.77
    
    -0.75
    tvguidetime
    -0.75
     odkazy
    -0.75
    Clik
    -0.75
    \{\\
    -0.75
    POSITIVE LOGITS
    #
    0.52
    b
    0.49
    ↵↵
    0.48
    vábbi
    0.47
    test
    0.45
     test
    0.45
    vue
    0.44
    Test
    0.44
    d
    0.43
    -
    0.43
    Activations Density 4.244%

    No Known Activations