© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8805
    Prev
    Next
    INDEX
    Explanations

    discourse markers like "either", "too", "anyway", or conversational fragments (like "ok, ^^").

    oai_token-act-pair · gemini-2.0-flash

    either

    np_max-act · 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
    <bos>
    -1.15
    NameInMap
    -0.85
     समीक्षाओं
    -0.82
    ]){
    
    -0.80
    AddTagHelper
    -0.80
    InjectAttribute
    -0.79
     cherchés
    -0.79
     Jefus
    -0.77
     uſe
    -0.77
     uſed
    -0.77
    POSITIVE LOGITS
     partito
    0.44
     anyway
    0.44
     anyways
    0.42
    splatz
    0.42
    chair
    0.42
    Props
    0.39
     darn
    0.39
     damn
    0.39
    agian
    0.38
    anyway
    0.38
    Activations Density 2.179%

    No Known Activations