© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3033
    Prev
    Next
    INDEX
    Explanations

    titles and descriptors of people

    oai_token-act-pair · gemini-2.0-flash

    Titles and organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    
    -0.56
     propOrder
    -0.53
    parsedMessage
    -0.50
    ształ
    -0.48
     kaarangay
    -0.47
    AppCompatTheme
    -0.46
     apellidos
    -0.45
    udesta
    -0.45
    ItemBackground
    -0.44
    ดัง
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.63
    出版年
    0.59
    migrationBuilder
    0.56
    Παραπομπές
    0.56
    脚注の使い方
    0.55
    stuhl
    0.53
    AtIndexPath
    0.52
    Kaynakça
    0.50
    ennia
    0.48
    LETS
    0.48
    Activations Density 3.911%

    No Known Activations