© 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. 3169
    Prev
    Next
    INDEX
    Explanations

    scientific text involving calculations, constants, and measurements

    oai_token-act-pair · gemini-2.0-flash

    scientific measurements

    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
     nakalista
    -0.95
    ècie
    -0.64
    AndroidJUnit
    -0.64
     handleMessage
    -0.64
    getMenuInflater
    -0.63
     air
    -0.60
     water
    -0.58
     ANCHE
    -0.57
     Autorisations
    -0.57
     burn
    -0.57
    POSITIVE LOGITS
    cal
    0.57
    W
    0.56
    Cal
    0.55
    K
    0.55
     cal
    0.54
     Cal
    0.52
    WebpackPlugin
    0.52
     K
    0.50
    kal
    0.50
    J
    0.48
    Activations Density 4.624%

    No Known Activations