© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10670
    Prev
    Next
    INDEX
    Explanations

    words associated with cause and effect relationships

    oai_token-act-pair · gemini-2.0-flash

    negative possibilities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     onCreateView
    -0.72
    iNdEx
    -0.67
    ]='\
    -0.66
    WEBPACK
    -0.64
     onOptions
    -0.60
    RegistryLite
    -0.57
    artifactId
    -0.57
    DispatchToProps
    -0.56
    Personendaten
    -0.56
    thalten
    -0.56
    POSITIVE LOGITS
     lead
    0.46
    fficking
    0.45
    :✨
    0.44
     beginnetje
    0.42
     Introducing
    0.40
    ştır
    0.40
     introduce
    0.39
    мар
    0.39
    testnet
    0.39
     pase
    0.39
    Activations Density 0.899%

    No Known Activations