© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8883
    Prev
    Next
    INDEX
    Explanations

    words containing the substrings "ask", "king", or "ties"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     виправивши
    -0.66
    MethodManager
    -0.65
     AssemblyCulture
    -0.61
     članak
    -0.60
    sidemargin
    -0.59
    Portály
    -0.59
    BeginContext
    -0.59
    θρώ
    -0.58
    Cordialement
    -0.56
    expandindo
    -0.56
    POSITIVE LOGITS
     task
    1.70
     tasks
    1.52
     Task
    1.44
    task
    1.38
    Task
    1.35
    tasks
    1.30
    Tasks
    1.27
     Tasks
    1.26
     TASK
    1.22
    TASK
    1.21
    Activations Density 0.721%

    No Known Activations