Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14517
    Prev
    Next
    INDEX
    Explanations

    strings of digits or dollar signs followed by digits

    oai_token-act-pair · gemini-2.0-flash

    Numerical values

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     thousands
    -1.65
     thousand
    -1.55
    thousands
    -1.44
     Thousands
    -1.42
     hundreds
    -1.34
    Thousands
    -1.31
     THOUS
    -1.30
    thousand
    -1.14
    hundreds
    -1.13
     Hundreds
    -1.10
    POSITIVE LOGITS
     NSCoder
    0.69
    DoubleQuotes
    0.66
    chitz
    0.63
    IntoConstraints
    0.62
     Normdatei
    0.62
     lenker
    0.60
    contentLoaded
    0.59
    protoimpl
    0.58
    URLException
    0.56
     تضيفلها
    0.56
    Activations Density 1.256%

    No Known Activations