© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12135
    Prev
    Next
    INDEX
    Explanations

    terms related to space, telescopes, and radio astronomy

    oai_token-act-pair · gemini-2.0-flash

    astronomy texts

    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
    rungsseite
    -0.70
    makeConstraints
    -0.69
    XmlAccessType
    -0.67
    IntoConstraints
    -0.65
     autorytatywna
    -0.63
    évaluateur
    -0.60
    MLLoader
    -0.60
    WithIOException
    -0.57
     estimés
    -0.55
    HostException
    -0.54
    POSITIVE LOGITS
     ویکی‌پدیا
    0.52
     Revised
    0.52
    heyd
    0.52
     apprehension
    0.50
    ocera
    0.49
    fras
    0.49
    andaag
    0.48
     cupid
    0.47
    tamento
    0.47
     Versa
    0.47
    Activations Density 1.202%

    No Known Activations