© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11459
    Prev
    Next
    INDEX
    Explanations

    a mix of words relating to amounts, testing, the year and legal documents.

    oai_token-act-pair · gemini-2.0-flash

    a or

    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
    rungsseite
    -0.99
    AddTagHelper
    -0.94
    MemoryWarning
    -0.93
    Personendaten
    -0.91
    MessageOf
    -0.91
    tvguidetime
    -0.84
     NSCoder
    -0.84
    reportWebVitals
    -0.83
     BrowserModule
    -0.82
    новништво
    -0.82
    POSITIVE LOGITS
    ↵↵
    0.49
     Page
    0.40
     secr
    0.40
    https
    0.39
     https
    0.39
     Nor
    0.37
    page
    0.37
    Page
    0.37
    <strong>
    0.36
    umia
    0.35
    Activations Density 24.464%

    No Known Activations