© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8265
    Prev
    Next
    INDEX
    Explanations

    scientific text about spin and charge

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    contentLoaded
    -0.92
     ویکی‌پدی
    -0.77
    reportWebVitals
    -0.75
    Portale
    -0.75
     estimés
    -0.71
    ArrowToggle
    -0.68
     snippetHide
    -0.67
    MLLoader
    -0.67
    InjectAttribute
    -0.65
     endblock
    -0.64
    POSITIVE LOGITS
    <bos>
    0.50
     Socialista
    0.49
     immagin
    0.49
     porcelaine
    0.46
     created
    0.44
    contentValues
    0.44
    nthetic
    0.43
    ed
    0.43
     project
    0.43
    立
    0.42
    Activations Density 5.080%

    No Known Activations