© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10538
    Prev
    Next
    INDEX
    Explanations

    words related to numeric comparisons, predictions and drug efficacy

    oai_token-act-pair · gemini-2.0-flash

    compare

    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
     makeStyles
    -0.68
     мәкал
    -0.65
    FTFY
    -0.63
     onCancelled
    -0.60
     Maki
    -0.60
     >=",
    -0.60
    FormTagHelper
    -0.58
    Simulated
    -0.57
    loyd
    -0.57
     يتيمه
    -0.57
    POSITIVE LOGITS
     stack
    0.94
     compares
    0.93
     compare
    0.90
    stack
    0.86
     stacks
    0.85
     Stack
    0.76
    Stack
    0.75
    compare
    0.74
     Compare
    0.65
     fair
    0.64
    Activations Density 2.117%

    No Known Activations