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. 14922
    Prev
    Next
    INDEX
    Explanations

    computer code and mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    code and math symbols

    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
     <<<<<<<<<<<<<<
    -0.85
    ’.”
    -0.63
    '."
    -0.53
    awtextra
    -0.50
    myapplication
    -0.50
     estekak
    -0.49
     latine
    -0.48
    üge
    -0.45
    scriptcase
    -0.45
     "..\..\
    -0.45
    POSITIVE LOGITS
    parsedMessage
    0.63
    şiv
    0.62
    InjectAttribute
    0.60
    ProcessEvent
    0.59
     noDo
    0.56
     كمان
    0.56
     endl
    0.54
    JspWriter
    0.53
    Insee
    0.52
     pic
    0.51
    Activations Density 4.217%

    No Known Activations