© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11876
    Prev
    Next
    INDEX
    Explanations

    uses the "dot" operator to access class members for `MediaType` objects

    oai_token-act-pair · gemini-2.0-flash

    dot

    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
    IsContent
    -0.68
    Datuak
    -0.57
    gpl
    -0.53
    andExpect
    -0.53
    SourceChecksum
    -0.52
     broad
    -0.52
    xase
    -0.51
    MockBean
    -0.50
     EconPapers
    -0.49
     poire
    -0.49
    POSITIVE LOGITS
    AnchorStyles
    0.51
    DotNetBar
    0.49
    WebServlet
    0.46
    󠁧
    0.46
     TextAlign
    0.46
    rigkeit
    0.45
    unzel
    0.44
     通販
    0.44
    öhe
    0.43
     kasarigan
    0.43
    Activations Density 0.165%

    No Known Activations