© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6300
    Prev
    Next
    INDEX
    Explanations

    language used in discussions or debates

    oai_token-act-pair · gemini-2.0-flash

    Related to "down"

    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
     BorderRadius
    -0.61
    Hochspringen
    -0.57
    czego
    -0.55
     classNames
    -0.54
     Polda
    -0.52
    +#+
    -0.50
    adaptiveStyles
    -0.49
    ]='\
    -0.49
    imental
    -0.48
    binant
    -0.48
    POSITIVE LOGITS
     down
    3.45
    down
    2.78
    Down
    2.64
     Down
    2.56
     DOWN
    2.42
    DOWN
    2.17
    downs
    1.90
    ダウン
    1.66
     downs
    1.64
    Downs
    1.43
    Activations Density 7.418%

    No Known Activations