© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4527
    Prev
    Next
    INDEX
    Explanations

    words and small phrases in a supportive or protective context

    oai_token-act-pair · gemini-2.0-flash

    protect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     protection
    -0.96
     protecting
    -0.94
     Protection
    -0.92
    Protection
    -0.91
     Protecting
    -0.90
     protect
    -0.90
    protection
    -0.90
    protect
    -0.87
    Protecting
    -0.84
     protective
    -0.82
    POSITIVE LOGITS
    脚注の使い方
    1.00
    
    0.75
    <bos>
    0.75
     utafitiHapana
    0.74
    رشف
    0.71
     disponibilités
    0.70
    Зноскі
    0.69
    pushFollow
    0.69
    Vidite
    0.68
    WithIOException
    0.67
    Activations Density 38.348%

    No Known Activations