© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15375
    Prev
    Next
    INDEX
    Explanations

    scientific studies and experiments related to learning, attention, and stimuli.

    oai_token-act-pair · gemini-2.0-flash

    Scientific research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     potenci
    -0.68
    potential
    -0.65
    rungsseite
    -0.65
    webElement
    -0.65
     Potential
    -0.64
    TagMode
    -0.63
    Personendaten
    -0.63
    Potential
    -0.63
    SequentialGroup
    -0.63
     تضيفلها
    -0.62
    POSITIVE LOGITS
    AccessorTable
    0.47
    WebServlet
    0.47
    ributions
    0.47
     disso
    0.45
     Attribution
    0.44
    shund
    0.43
    ERIES
    0.43
    NUMX
    0.41
    rivit
    0.41
    vaadin
    0.41
    Activations Density 0.815%

    No Known Activations