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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10939
    Prev
    Next
    INDEX
    Explanations

    code snippets and computer programming terminology related to files and loading data

    oai_token-act-pair · gemini-2.0-flash

    identifiers related to data handling and memory management

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

    programming

    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
    WriteTagHelper
    -0.69
    PreferredItem
    -0.63
     Majefty
    -0.61
     Inflate
    -0.59
     newBuilder
    -0.58
     الرياضيه
    -0.57
    يكب
    -0.56
     perfons
    -0.56
    QMetaType
    -0.55
     nudity
    -0.54
    POSITIVE LOGITS
    DebuggerNonUser
    0.62
     internal
    0.61
     external
    0.50
    TypedDataSet
    0.48
     External
    0.48
    rapp
    0.47
    ешь
    0.46
    quested
    0.45
    External
    0.45
     app
    0.45
    Activations Density 3.917%

    No Known Activations