© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9114
    Prev
    Next
    INDEX
    Explanations

    math equations and their related variables/functions with emphasis on derivatives

    oai_token-act-pair · gemini-2.0-flash

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    rt
    -0.98
    DT
    -0.96
    RT
    -0.92
     BT
    -0.91
    BT
    -0.91
    nt
    -0.90
     RT
    -0.87
     DT
    -0.86
    bt
    -0.85
    MT
    -0.84
    POSITIVE LOGITS
    webElementXpaths
    0.71
    WebControls
    0.68
    ThroughAttribute
    0.65
    ArrowToggle
    0.63
    Obrázky
    0.60
    IsPostBack
    0.60
    brigens
    0.59
    getragen
    0.58
    ContentAlignment
    0.57
     ruota
    0.56
    Activations Density 10.048%

    No Known Activations