© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5421
    Prev
    Next
    INDEX
    Explanations

    words related to software, computing, and IT management.

    oai_token-act-pair · gemini-2.0-flash

    terms related to solutions and authentication

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

    solution

    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
     beginnetje
    -0.51
     "));
    -0.48
    ())).
    -0.47
    Lugares
    -0.46
    >");
    
    -0.46
    тьи
    -0.46
     níveis
    -0.43
    Demografia
    -0.43
    titleMargin
    -0.42
    PyErr
    -0.42
    POSITIVE LOGITS
     solution
    0.99
     SOLUTION
    0.92
     Solution
    0.90
    solution
    0.89
     solutions
    0.85
     Lösung
    0.85
     autorytatywna
    0.84
     solução
    0.83
     solución
    0.79
    IntoConstraints
    0.79
    Activations Density 2.151%

    No Known Activations