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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14642
    Prev
    Next
    INDEX
    Explanations

    references to locations within the Marvel comic universe

    oai_token-act-pair · gemini-2.0-flash

    mythology and fiction

    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
    oneofs
    -0.58
    ensibility
    -0.57
    complexType
    -0.55
     geox
    -0.54
    StructEnd
    -0.54
     Efq
    -0.54
    ÓS
    -0.53
    gerufen
    -0.52
    Jem
    -0.52
     storici
    -0.52
    POSITIVE LOGITS
    DoubleQuotes
    0.56
     Pend
    0.51
    ьаж
    0.49
     Murphy
    0.49
    PropertyType
    0.49
    Arthur
    0.49
     Arthur
    0.49
    kháu
    0.49
     Par
    0.47
     Accesat
    0.46
    Activations Density 1.405%

    No Known Activations