© 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. 9125
    Prev
    Next
    INDEX
    Explanations

    phrases made of multiple short words related to low to the ground

    oai_token-act-pair · gemini-2.0-flash

    say "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
    beiro
    -0.59
    semibold
    -0.54
     سكانية
    -0.54
    NOPQRST
    -0.54
    stätte
    -0.54
    (&:
    -0.54
    λικά
    -0.52
    GROSS
    -0.52
    hies
    -0.51
    getOut
    -0.51
    POSITIVE LOGITS
     down
    3.28
    down
    2.69
    Down
    2.47
     Down
    2.42
     DOWN
    2.38
    DOWN
    2.14
    downs
    1.97
     downs
    1.89
    ダウン
    1.77
     dow
    1.69
    Activations Density 7.236%

    No Known Activations