© 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. 11700
    Prev
    Next
    INDEX
    Explanations

    C code syntax

    oai_token-act-pair · gemini-2.0-flash

    foreign or technical identifiers

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

    Code, paths, and variables

    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
    </b>
    -0.68
    </i>
    -0.65
     others
    -0.62
     [
    -0.61
     it
    -0.60
     
    -0.59
    </strong>
    -0.59
     the
    -0.57
      
    -0.56
    asa
    -0.56
    POSITIVE LOGITS
     Мексичка
    0.92
     متعلقه
    0.83
     étoient
    0.83
    SharedDtor
    0.72
     onAnimation
    0.72
    setupUi
    0.71
    Билгалдахарш
    0.69
    posedge
    0.68
    expandindo
    0.67
     cdti
    0.67
    Activations Density 5.448%

    No Known Activations