Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14397
    Prev
    Next
    INDEX
    Explanations

    language relating to supporting a target population through charitable or health-related programs

    oai_token-act-pair · gemini-2.0-flash

    "in"

    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
    MigrationBuilder
    -0.87
    reportWebVitals
    -0.78
    IndentedString
    -0.75
    WebVitals
    -0.74
     CURIAM
    -0.71
    NameInMap
    -0.70
     يتيمه
    -0.69
    脚注の使い方
    -0.69
    Datuak
    -0.68
    RTLD
    -0.68
    POSITIVE LOGITS
     in
    0.83
    อยู่ใน
    0.66
    ใน
    0.63
     into
    0.62
     في
    0.61
    inthe
    0.60
     dalam
    0.58
     dans
    0.57
     nella
    0.57
     trong
    0.56
    Activations Density 1.893%

    No Known Activations