© 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. 5624
    Prev
    Next
    INDEX
    Explanations

    instances of the word "find" and code snippets in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    Code/Mixed Language

    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
     stie
    -0.51
     secondary
    -0.51
    Portály
    -0.50
     Secondary
    -0.49
     ángel
    -0.47
     Indus
    -0.46
    null
    -0.45
     Comstock
    -0.45
     sej
    -0.45
     tarde
    -0.44
    POSITIVE LOGITS
    Heres
    1.02
     voici
    1.02
    voici
    0.91
     here
    0.85
     للمعارف
    0.84
    Voici
    0.83
    <bos>
    0.83
     heres
    0.82
    Вот
    0.81
     işte
    0.80
    Activations Density 0.874%

    No Known Activations