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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1143
    Prev
    Next
    INDEX
    Explanations

    problems and errors

    np_max-act-logits · gemini-2.0-flash

    words and phrases related to problem solving and diagnosis of technical issues

    oai_token-act-pair · gemini-2.0-flash

    technical jargon/gibberish

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    ={({
    -0.50
    InSection
    -0.50
    Worked
    -0.49
    oane
    -0.49
    XmlAccessorType
    -0.49
    americanas
    -0.46
     weaker
    -0.46
    ویزی
    -0.46
     >=",
    -0.46
     []:
    -0.45
    POSITIVE LOGITS
     Roskov
    0.72
     esternos
    0.60
    حوالہ
    0.60
     AssemblyProduct
    0.59
     cherchés
    0.52
     disponibilités
    0.50
    Indented
    0.49
    Smarty
    0.48
    Searcher
    0.48
     &'
    0.48
    Activations Density 2.904%

    No Known Activations