Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9647
    Prev
    Next
    INDEX
    Explanations

    words and numbers in mathematical texts that are related to vector spaces and other related concepts

    oai_token-act-pair · gemini-2.0-flash

    complex systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     space
    -1.10
     system
    -1.07
     System
    -1.02
    space
    -0.97
    System
    -0.93
     Space
    -0.93
    system
    -0.93
     SYSTEM
    -0.92
    Space
    -0.87
     espacio
    -0.83
    POSITIVE LOGITS
    ToTensor
    0.56
    Хьажоргаш
    0.53
     shoe
    0.51
    weł
    0.51
    apunov
    0.50
    CodeAttribute
    0.50
    retmen
    0.49
    ⓧ
    0.49
    setObjectName
    0.48
    DrawerToggle
    0.47
    Activations Density 2.816%

    No Known Activations