© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16011
    Prev
    Next
    INDEX
    Explanations

    Java import statements followed by the tokens "org" and "com."

    oai_token-act-pair · gemini-2.0-flash

    .com and .org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    UnknownFieldSet
    -0.82
    ləş
    -0.79
     CommonModule
    -0.75
     تضيفلها
    -0.75
    WithMany
    -0.71
     AssemblyProduct
    -0.71
     وتسجيلات
    -0.70
    #
    -0.70
     ویکی‌پدیای
    -0.68
    UnknownFields
    -0.68
    POSITIVE LOGITS
     utafitiHapana
    0.56
     Co
    0.49
    dut
    0.48
    >();
    0.46
     Loy
    0.46
     While
    0.45
    masing
    0.44
     Naw
    0.44
    Allowed
    0.44
     EM
    0.44
    Activations Density 0.205%

    No Known Activations