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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13580
    Prev
    Next
    INDEX
    Explanations

    code involving Java class names and Android-specific function calls

    oai_token-act-pair · gemini-2.0-flash

    Period token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ddelweddau
    -1.13
     Roskov
    -1.10
    Personensuche
    -1.05
     متعلقه
    -1.00
     CreateTagHelper
    -0.98
     resourceCulture
    -0.97
     <>",
    -0.95
     itſelf
    -0.94
     propOrder
    -0.94
    сылкі
    -0.92
    POSITIVE LOGITS
    ↵↵
    0.52
     
    0.51
    us
    0.50
     that
    0.48
     "
    0.47
    <eos>
    0.47
    ;
    0.47
     Mac
    0.46
     G
    0.45
    лла
    0.44
    Activations Density 4.122%

    No Known Activations