© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9485
    Prev
    Next
    INDEX
    Explanations

    questions and answers, headings or categories, references, code snippets, and links, i.e., segments from digital documents

    oai_token-act-pair · gemini-2.0-flash

    start of new article

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     nakalista
    -0.61
    ThroughAttribute
    -0.52
     welcome
    -0.49
    olari
    -0.48
    ellyn
    -0.46
     saites
    -0.46
    ViewFeatures
    -0.46
     nahilalakip
    -0.44
    idom
    -0.44
    <eos>
    -0.43
    POSITIVE LOGITS
     referrerpolicy
    0.81
    Zitat
    0.62
    ("")]
    0.62
     }}$}
    0.61
    --}}
    0.59
    ')}}
    0.58
    تحميل
    0.57
    Wichtig
    0.57
    '])){
    0.57
    Răsp
    0.57
    Activations Density 13.283%

    No Known Activations