© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6246
    Prev
    Next
    INDEX
    Explanations

    LaTeX code related to figures

    oai_token-act-pair · gemini-2.0-flash

    LaTeX document formatting elements

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

    width

    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
    aarrggbb
    -1.07
    
    -1.07
     itſelf
    -1.05
     <=",
    -1.04
    IndentedString
    -1.04
    Personendaten
    -1.04
    ValueStyle
    -1.00
    contentLoaded
    -1.00
    Lähteet
    -1.00
     Theſe
    -0.98
    POSITIVE LOGITS
     [
    0.71
    ,
    0.69
     (
    0.67
     
    0.62
    </i>
    0.60
    [
    0.60
     T
    0.60
     two
    0.59
    <i>
    0.58
    .
    0.57
    Activations Density 0.467%

    No Known Activations