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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6521
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and related vocabulary, especially integrals and transformations

    oai_token-act-pair · gemini-2.0-flash

    integration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.76
     
    -0.71
    '
    -0.60
     u
    -0.58
     "
    -0.58
     A
    -0.57
     a
    -0.57
     -
    -0.56
     (
    -0.55
     The
    -0.54
    POSITIVE LOGITS
     contextLoads
    1.06
    SequentialGroup
    1.04
     GenerationType
    1.02
     iſt
    0.97
    istoitu
    0.95
    Демографія
    0.94
     وتسجيلات
    0.92
     ―――――
    0.91
    VersionUID
    0.91
     ſind
    0.91
    Activations Density 5.747%

    No Known Activations