© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 367
    Prev
    Next
    INDEX
    Explanations

    a variety of words related to manufacturing, light, cooking, gas, cooling, and color.

    oai_token-act-pair · gemini-2.0-flash

    Mechanical processes

    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
     سكانية
    -0.65
     للاسماء
    -0.52
     Мексичка
    -0.47
    المشاركات
    -0.44
    __);
    -0.41
     ;
    
    -0.41
    ,‎
    -0.40
    '),
    
    -0.39
    “”
    -0.39
    timewa
    -0.39
    POSITIVE LOGITS
    AnchorStyles
    0.65
     exécu
    0.63
    alnız
    0.62
    apunov
    0.61
    transQ
    0.60
    WRAPPER
    0.57
    Curator
    0.55
     exemplaires
    0.55
     aéri
    0.55
     Shelf
    0.55
    Activations Density 2.947%

    No Known Activations