© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1651
    Prev
    Next
    INDEX
    Explanations

    web addresses, email addresses, and other website-related words

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    шом
    -0.49
    estie
    -0.41
     broken
    -0.41
    ثيل
    -0.40
    theid
    -0.40
    PyErr
    -0.39
    Архівовано
    -0.38
    டன்
    -0.38
    jobb
    -0.38
    omir
    -0.38
    POSITIVE LOGITS
    OGND
    0.91
     CreateTagHelper
    0.75
    <bos>
    0.71
     JpaRepository
    0.69
    ftagPool
    0.66
     propOrder
    0.64
     ujednoznacz
    0.64
     Familienname
    0.63
    曖昧さ回避
    0.62
     initComponents
    0.62
    Activations Density 31.978%

    No Known Activations