© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8146
    Prev
    Next
    INDEX
    Explanations

    negative mentions of the Patriot Act and treason around the 9/11 attacks

    oai_token-act-pair · gemini-2.0-flash

    September

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ⓧ
    -0.84
    
    -0.82
     nahilalakip
    -0.79
     дописавши
    -0.75
    mybatisplus
    -0.75
    expandindo
    -0.74
    Autoritní
    -0.73
     Chwiliwch
    -0.72
     AttributeSet
    -0.72
    MeasureSpec
    -0.72
    POSITIVE LOGITS
     September
    1.09
     Sept
    1.05
    September
    0.91
    Sept
    0.88
     september
    0.77
     Sep
    0.76
     septembre
    0.75
     SEPTEMBER
    0.72
     сентября
    0.72
     Septem
    0.71
    Activations Density 0.837%

    No Known Activations