© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14711
    Prev
    Next
    INDEX
    Explanations

    parts of names with "Al", "Sa", and "raz"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Size
    -0.71
     tamaños
    -0.69
     Sizes
    -0.66
     sizes
    -0.65
    Size
    -0.63
     Large
    -0.62
     Medium
    -0.62
     size
    -0.61
     SIZE
    -0.61
     Größe
    -0.60
    POSITIVE LOGITS
    Begriffsklä
    0.62
    withIdentifier
    0.60
     ddelweddau
    0.58
    WithIdentifier
    0.57
    })));
    0.55
    WithIOException
    0.55
     ovaries
    0.54
     tillage
    0.53
     conjuncti
    0.53
     sauce
    0.52
    Activations Density 0.391%

    No Known Activations