© 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. 9182
    Prev
    Next
    INDEX
    Explanations

    words related to physics, theoretical constructs, and complex mathematical notation, with some instances of web page formatting code also triggering it

    oai_token-act-pair · gemini-2.0-flash

    symmetry

    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
     يتيمه
    -0.47
     RTV
    -0.47
    ณะ
    -0.45
     per
    -0.45
    ẾT
    -0.45
    iteness
    -0.44
     sonore
    -0.44
     tốc
    -0.42
     Wet
    -0.41
    ilig
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    1.05
    expandindo
    0.90
    <bos>
    0.78
    IsMutable
    0.77
    WEBPACK
    0.76
     שוליים
    0.74
    ChildScrollView
    0.73
    IsContent
    0.72
     <<<<<<<<<<<<<<
    0.71
    AndEndTag
    0.70
    Activations Density 1.105%

    No Known Activations