© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1322
    Prev
    Next
    INDEX
    Explanations

    a mix of scientific terms, including chemical elements and some plant-related words

    oai_token-act-pair · gemini-2.0-flash

    sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     quelcon
    -0.60
    ortun
    -0.59
     actuels
    -0.57
     FontWeight
    -0.57
    psack
    -0.56
     CHAPITRE
    -0.56
     <>",
    -0.56
    Ҭ
    -0.55
    parsedMessage
    -0.55
     différente
    -0.55
    POSITIVE LOGITS
    <bos>
    0.95
    /*
    0.75
    /**
    0.61
    HttpFoundation
    0.46
    <
    0.46
    ως
    0.46
    zbęd
    0.45
    Vir
    0.45
    نسي
    0.44
     kiệm
    0.44
    Activations Density 13.280%

    No Known Activations