© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15000
    Prev
    Next
    INDEX
    Explanations

    documentation of the negative side effects and toxicity of medical treatments

    oai_token-act-pair · gemini-2.0-flash

    side

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    发表于
    -0.57
    jstor
    -0.57
    WithIOException
    -0.52
    endcsname
    -0.49
    twimg
    -0.47
    
    -0.46
    ########.
    -0.46
    χρι
    -0.45
    valry
    -0.44
    ,:)
    -0.43
    POSITIVE LOGITS
     side
    2.44
     Side
    2.11
    Side
    2.11
     SIDE
    1.95
    side
    1.91
    SIDE
    1.70
     sides
    1.33
     adverse
    1.31
    サイド
    1.17
     samping
    1.15
    Activations Density 3.052%

    No Known Activations