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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5792
    Prev
    Next
    INDEX
    Explanations

    the word "water" and related words like "aquatic," "marine," or words ending in "-ine" used in a water context

    oai_token-act-pair · gemini-2.0-flash

    water

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SharedDtor
    -0.57
    MergeFrom
    -0.51
     numerus
    -0.48
     jLabel
    -0.47
     SPEC
    -0.47
    gering
    -0.46
    dart
    -0.46
    SPEC
    -0.44
    AnchorTagHelper
    -0.44
    oan
    -0.44
    POSITIVE LOGITS
    Soorten
    0.60
    
    0.59
    mobileqq
    0.57
    клопе
    0.57
    WaitGroup
    0.57
    bufio
    0.55
    曖昧さ回避
    0.54
    melons
    0.54
     SafeMath
    0.50
    logged
    0.50
    Activations Density 0.464%

    No Known Activations