© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4498
    Prev
    Next
    INDEX
    Explanations

    java-related keywords such as javax, GenerationType, and java

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
    !';
    -0.74
    ."]
    -0.74
    !")
    
    -0.73
    ^(@)
    -0.68
     XNUMX
    -0.66
     """
    
    -0.64
    ,‎
    -0.63
    .[/
    -0.63
    — 
    -0.63
    '>
    
    -0.62
    POSITIVE LOGITS
     Magee
    0.49
    mybatisplus
    0.48
     useRef
    0.48
    sass
    0.48
    Географи
    0.47
    Становништво
    0.47
    sm
    0.47
    jing
    0.47
    exécution
    0.46
    bestand
    0.46
    Activations Density 7.278%

    No Known Activations