© 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-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10132
    Prev
    Next
    INDEX
    Explanations

    code snippets related to users, especially usernames, avatars, and screen names

    oai_token-act-pair · gemini-2.0-flash

    coding or programming related elements

    np_token-act-pair-logits · gpt-4o-mini
    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
     المق
    -0.51
     mapStateToProps
    -0.50
    Hrsg
    -0.50
    NgModule
    -0.49
    <?,
    -0.48
     <=",
    -0.48
    iseta
    -0.46
    snprintf
    -0.46
    omma
    -0.45
    Holding
    -0.45
    POSITIVE LOGITS
    发表于
    0.58
    tagHelperRunner
    0.58
    Personensuche
    0.56
     Vikipedi
    0.52
    cplusplus
    0.52
     مرئيه
    0.49
    __(/*!
    0.49
    <thead>
    0.47
    pyx
    0.47
    /*
    0.47
    Activations Density 1.002%

    No Known Activations