© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9663
    Prev
    Next
    INDEX
    Explanations

    math papers

    oai_token-act-pair · gemini-2.0-flash

    series

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    \{\\
    -0.73
    <bos>
    -0.62
    Begriffsklä
    -0.57
    findpost
    -0.56
    andowski
    -0.55
    AnchorStyles
    -0.54
    нибудь
    -0.51
    onViewCreated
    -0.50
     särsk
    -0.49
    一方面
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.63
    IndentedString
    0.61
    localctx
    0.60
    CompilerServices
    0.56
    قایناقلار
    0.54
    byter
    0.54
    PreferredItem
    0.54
    CharStream
    0.53
     Erl
    0.53
    LayoutStyle
    0.52
    Activations Density 4.208%

    No Known Activations