© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12901
    Prev
    Next
    INDEX
    Explanations

    words associated with metalworking and manufacturing

    oai_token-act-pair · gemini-2.0-flash

    metal casting

    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
    windowFixed
    -0.56
     Debt
    -0.50
     zapo
    -0.50
     debt
    -0.50
    endpush
    -0.49
     vermelhas
    -0.49
     Beep
    -0.47
     تضيفلها
    -0.47
     debts
    -0.46
    akuza
    -0.46
    POSITIVE LOGITS
     cast
    0.90
     Cast
    0.76
    Cast
    0.71
    cast
    0.68
     consultato
    0.68
     CAST
    0.63
    CrossRef
    0.62
     TextInputType
    0.62
    QMetaType
    0.62
     mild
    0.60
    Activations Density 1.424%

    No Known Activations