© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4788
    Prev
    Next
    INDEX
    Explanations

    language related to legal actions, political process, and investigations.

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

    np_token-act-pair-logits · gpt-4o-mini

    News articles/excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    unknownFields
    -0.49
    res
    -0.42
    <sup>
    -0.41
     occhiali
    -0.40
     Universitas
    -0.39
    ahr
    -0.38
     Prime
    -0.38
     
    -0.38
     res
    -0.38
    localVar
    -0.37
    POSITIVE LOGITS
    UserScript
    0.91
    Personendaten
    0.91
    MemoryWarning
    0.81
     StatefulWidget
    0.80
    IsContent
    0.75
     createState
    0.74
    poons
    0.72
    
    0.72
    RectangleBorder
    0.72
    CrossRef
    0.70
    Activations Density 3.135%

    No Known Activations