© 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. 12602
    Prev
    Next
    INDEX
    Explanations

    words that indicate the content being described is negatively impacted, especially in the context of spoilers or sports

    oai_token-act-pair · gemini-2.0-flash

    ruin

    np_max-act · 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
    CODEC
    -0.56
     pymongo
    -0.56
     commissioner
    -0.52
    }{{\
    -0.50
     V
    -0.48
    </b>
    -0.48
    Izvori
    -0.47
     []
    -0.47
    állítás
    -0.46
     useRef
    -0.46
    POSITIVE LOGITS
     spoiling
    0.75
    GEBURTSDATUM
    0.71
    DockStyle
    0.71
     ruining
    0.71
     spoilt
    0.69
    رشف
    0.68
    ftagPool
    0.68
    Попис
    0.66
    下载附件
    0.66
     betweenstory
    0.66
    Activations Density 1.030%

    No Known Activations