© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4060
    Prev
    Next
    INDEX
    Explanations

    C/C++ code syntax, including keywords, operators, and function names related to memory manipulation and string operations, as well as angle brackets.

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    defer
    -0.56
     Vernunft
    -0.54
     plagioclase
    -0.54
    DebuggerNonUser
    -0.54
     knji
    -0.52
    UNRELATED
    -0.48
     tightness
    -0.46
    Abit
    -0.45
     kapcs
    -0.45
     jegy
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.77
     onCreateView
    0.76
    IsContent
    0.73
     snippetHide
    0.68
     !!}
    0.66
    PRNewswire
    0.64
    CodedInputStream
    0.64
    "])
    0.64
    TextSpan
    0.64
    AutoScale
    0.63
    Activations Density 0.706%

    No Known Activations