© 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. 12714
    Prev
    Next
    INDEX
    Explanations

    words and phrases about systems and institutions

    oai_token-act-pair · gemini-2.0-flash

    base, foundation

    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
     core
    -0.96
     fundamental
    -0.96
     basic
    -0.89
    Essential
    -0.89
     essential
    -0.88
    basic
    -0.87
    Basic
    -0.87
     essentials
    -0.87
    core
    -0.86
     Basic
    -0.86
    POSITIVE LOGITS
    脚注の使い方
    0.80
     ujednoznacz
    0.58
     StatefulWidget
    0.57
    Бахар
    0.57
     Numerade
    0.57
     $__
    0.56
     PhpStorm
    0.56
     ProtoMessage
    0.56
     StatelessWidget
    0.55
     متحده
    0.55
    Activations Density 39.383%

    No Known Activations