© 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. 11553
    Prev
    Next
    INDEX
    Explanations

    java code related to JSON data

    oai_token-act-pair · gemini-2.0-flash

    function calls or method signatures

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

    Code snippets

    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
     class
    -2.75
    class
    -2.38
     classes
    -2.33
     classe
    -2.02
     Classes
    -1.98
     Class
    -1.96
    Class
    -1.88
    classes
    -1.87
    Classes
    -1.83
     CLASS
    -1.77
    POSITIVE LOGITS
    kuuta
    0.42
    городи
    0.36
    ust
    0.36
    ux
    0.35
    tees
    0.35
    ThemeProvider
    0.34
    (*
    0.34
    ところ
    0.34
    بان
    0.33
     scio
    0.33
    Activations Density 0.748%

    No Known Activations