© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4865
    Prev
    Next
    INDEX
    Explanations

    LaTeX math code with the word "protect" and the letters "dep".

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.94
     initWithFrame
    -0.42
    ėtų
    -0.42
     Esper
    -0.42
    2
    -0.40
    ↵↵
    -0.40
    FormUrlEncoded
    -0.39
    T
    -0.39
    O
    -0.38
    matrix
    -0.38
    POSITIVE LOGITS
    
    1.02
    ThroughAttribute
    0.84
     ligiloj
    0.83
    GraphicsUnit
    0.79
    ItemBackground
    0.77
     CreateTagHelper
    0.77
    complexContent
    0.77
    XmlAccessType
    0.76
    AutoScaleMode
    0.75
    oredCriteria
    0.73
    Activations Density 6.785%

    No Known Activations