© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6254
    Prev
    Next
    INDEX
    Explanations

    words associated with inventions, organizations, and dates

    oai_token-act-pair · gemini-2.0-flash

    something started/launched

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     tonight
    -0.58
     tomorrow
    -0.56
     today
    -0.56
     amanhã
    -0.53
     zufolge
    -0.52
     itſelf
    -0.52
     Tonight
    -0.51
    GraphicsUnit
    -0.51
    usto
    -0.50
     GetEnumerator
    -0.50
    POSITIVE LOGITS
     launched
    1.11
     debuted
    0.92
     arrived
    0.88
     released
    0.88
    launched
    0.85
     began
    0.85
     launch
    0.83
     Launched
    0.82
     started
    0.80
     premiered
    0.79
    Activations Density 3.936%

    No Known Activations