© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8855
    Prev
    Next
    INDEX
    Explanations

    words and phrases common on websites, especially those relating to blog posts and professional conferences or events.

    oai_token-act-pair · gemini-2.0-flash

    tech-related terms and technologies

    np_token-act-pair-logits · gpt-4o-mini

    software/tech

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    /-/
    -0.46
    次代
    -0.41
     castelo
    -0.40
    ródło
    -0.39
     classi
    -0.38
    lassified
    -0.38
     classific
    -0.37
     Zü
    -0.37
    classi
    -0.37
     geste
    -0.37
    POSITIVE LOGITS
     Hadoop
    0.95
     Microsoft
    0.94
     Linux
    0.91
     Java
    0.90
     Android
    0.90
    Android
    0.87
    Microsoft
    0.85
     SharePoint
    0.85
     WordPress
    0.84
     BrowserModule
    0.82
    Activations Density 9.557%

    No Known Activations