© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6523
    Prev
    Next
    INDEX
    Explanations

    the word fragment "de" followed by words having to do with office or camp

    oai_token-act-pair · gemini-2.0-flash

    weather/climate information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ientôt
    -0.65
    timewa
    -0.63
     chloroform
    -0.59
     néer
    -0.59
    ärna
    -0.58
    complexType
    -0.57
     kuiten
    -0.57
    Pautan
    -0.57
     nemat
    -0.56
     tetrach
    -0.56
    POSITIVE LOGITS
    <bos>
    1.02
    AddTagHelper
    0.63
    '])){
    
    0.61
    MigrationBuilder
    0.61
    ']))
    
    0.60
    })`
    0.60
    ']);
    
    0.60
    AnchorTagHelper
    0.59
    '))
    
    0.59
    ']?>
    0.58
    Activations Density 0.116%

    No Known Activations