© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14501
    Prev
    Next
    INDEX
    Explanations

    terms related to named things, organizations, projects, awards, categories and places

    oai_token-act-pair · gemini-2.0-flash

    sports, ships and trials

    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
    <bos>
    -0.59
    ChildScrollView
    -0.57
    drawiam
    -0.55
    awtextra
    -0.53
    tersebut
    -0.52
    early
    -0.51
    السكان
    -0.51
    Źródło
    -0.50
     Abbé
    -0.50
    SpringBootTest
    -0.50
    POSITIVE LOGITS
    WebElementEntity
    0.69
    تقاوى
    0.66
    ViewFeatures
    0.59
    makeText
    0.55
     faisons
    0.50
    tonode
    0.49
    +#+
    0.49
    息
    0.48
    /*---
    0.47
     étanche
    0.47
    Activations Density 6.172%

    No Known Activations