© 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. 10665
    Prev
    Next
    INDEX
    Explanations

    text related to the insurance industry

    oai_token-act-pair · gemini-2.0-flash

    insurance

    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
     Broker
    -0.54
     geleden
    -0.53
     Brokers
    -0.52
    SizeMode
    -0.51
     broker
    -0.51
    oneof
    -0.51
     brokers
    -0.47
    POSED
    -0.46
    idän
    -0.45
     Write
    -0.45
    POSITIVE LOGITS
    PerformLayout
    0.78
     surla
    0.61
     typelib
    0.60
    ikiki
    0.57
     NSCoder
    0.56
     Administrativna
    0.54
     oprot
    0.54
     Alive
    0.53
    amentals
    0.53
    amental
    0.52
    Activations Density 1.129%

    No Known Activations