© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10061
    Prev
    Next
    INDEX
    Explanations

    a mix of programming and technical terms, along with references to space and servers.

    oai_token-act-pair · gemini-2.0-flash

    Coding, Minecraft, and Space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    FileVersion
    -0.43
    dl
    -0.43
     rowspan
    -0.43
    frequency
    -0.41
    bumptech
    -0.41
    ysty
    -0.40
    da
    -0.40
     PyTuple
    -0.40
     lccn
    -0.39
    ialog
    -0.39
    POSITIVE LOGITS
    DockStyle
    0.98
    Aiheesta
    0.86
     متعلقه
    0.82
     snippetHide
    0.82
    :+:
    0.82
     صوتيه
    0.80
    aarrggbb
    0.74
    errHandler
    0.74
    AntiForgeryToken
    0.73
     Meksiku
    0.73
    Activations Density 2.402%

    No Known Activations