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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1310
    Prev
    Next
    INDEX
    Explanations

    dates, times, geographic coordinates, and related text

    oai_token-act-pair · gemini-2.0-flash

    Geographical coordinates

    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
    cards
    -0.47
    Errorf
    -0.45
    ivan
    -0.44
    
    -0.41
    makeConstraints
    -0.40
     Ripper
    -0.40
    wera
    -0.39
    ikon
    -0.39
    compose
    -0.39
    бло
    -0.39
    POSITIVE LOGITS
     Jefus
    0.81
     pleaſure
    0.80
     myſelf
    0.78
     referenties
    0.77
     HasFactory
    0.75
    WebVitals
    0.74
     виправивши
    0.73
    قایناق‌لار
    0.73
     للمعارف
    0.73
     Monfieur
    0.73
    Activations Density 14.904%

    No Known Activations