© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4949
    Prev
    Next
    INDEX
    Explanations

    prepositions and linking words

    oai_token-act-pair · gemini-2.0-flash

    programming syntax and special characters

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    InjectAttribute
    -0.60
    AnimationsModule
    -0.54
    setVerticalGroup
    -0.54
    SequentialGroup
    -0.52
     StatefulWidget
    -0.51
     BoxDecoration
    -0.50
     operativo
    -0.50
     OkHttpClient
    -0.49
     of
    -0.48
    OfWork
    -0.47
    POSITIVE LOGITS
    transQ
    0.64
    {}'.
    0.63
    {}".
    0.60
    webElementXpaths
    0.59
     varying
    0.59
     ?>/
    0.58
    ://$
    0.57
     Савезне
    0.56
    %";
    0.56
    %)$
    0.55
    Activations Density 17.598%

    No Known Activations