© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5592
    Prev
    Next
    INDEX
    Explanations

    HTML elements or attributes, specifically those related to links, stylesheets and file paths

    oai_token-act-pair · gemini-2.0-flash

    HTML link attributes

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

    ="

    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
    labus
    -0.50
     CommandType
    -0.46
     Boulogne
    -0.44
    mocha
    -0.44
     للمعارف
    -0.43
    -
    -0.42
     chêne
    -0.41
    expérience
    -0.41
     اط
    -0.40
    PTT
    -0.39
    POSITIVE LOGITS
    تقاوى
    0.90
    InjectAttribute
    0.80
    ObjectContext
    0.73
    SharedDtor
    0.72
    évaluateur
    0.69
    SequentialGroup
    0.69
     Paglinawan
    0.68
    makeConstraints
    0.67
     المعيارى
    0.67
    IntoConstraints
    0.65
    Activations Density 0.456%

    No Known Activations