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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3739
    Prev
    Next
    INDEX
    Explanations

    words related to data pairs and sets in a computational or mathematical context

    oai_token-act-pair · gemini-2.0-flash

    pairs

    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
    ↵↵
    -0.67
     
    -0.61
     name
    -0.61
    ,
    -0.55
    ↵
    -0.55
    :
    -0.54
     R
    -0.53
     "
    -0.52
     [
    -0.52
     for
    -0.51
    POSITIVE LOGITS
    SharedDtor
    1.20
    存于互联网档案馆
    1.19
    ThroughAttribute
    1.02
    UserScript
    1.00
    NUMX
    0.98
     виправивши
    0.97
     ujednoznacz
    0.94
     vPvB
    0.94
     الرياضيه
    0.94
     IBOutlet
    0.94
    Activations Density 2.806%

    No Known Activations