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. 5744
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    specific LaTeX command patterns

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

    Code and equations

    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
     ModelExpression
    -0.65
     AssemblyTitle
    -0.61
    Batis
    -0.52
    Cordialement
    -0.52
    +#+
    -0.52
    mbira
    -0.50
    subscribers
    -0.50
    endphp
    -0.49
    SuppressLint
    -0.49
    UTER
    -0.48
    POSITIVE LOGITS
    новниш
    0.60
     فريبيس
    0.59
    stay
    0.59
     المعيارى
    0.59
    Демографія
    0.58
     umbi
    0.57
    Personendaten
    0.54
     Aérea
    0.53
     stay
    0.52
     STAY
    0.52
    Activations Density 0.224%

    No Known Activations