© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13780
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to video or data compression

    oai_token-act-pair · gemini-2.0-flash

    media file formats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ftagPool
    -0.79
    DoubleQuotes
    -0.76
    ConstraintMaker
    -0.71
     ivelany
    -0.70
    IUrlHelper
    -0.69
    exitRule
    -0.67
    وأضاف
    -0.66
     चीज़ों
    -0.65
     BoxFit
    -0.65
    ThroughAttribute
    -0.65
    POSITIVE LOGITS
    Portale
    0.57
    CodedInputStream
    0.54
     Ev
    0.49
     files
    0.47
     pod
    0.47
     menus
    0.47
    omla
    0.47
     ос
    0.46
    nambuco
    0.45
     Con
    0.44
    Activations Density 12.349%

    No Known Activations