© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13524
    Prev
    Next
    INDEX
    Explanations

    the word "trick".

    oai_token-act-pair · gemini-2.0-flash

    trick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     trick
    -0.96
     Commerce
    -0.92
    Commerce
    -0.91
    commerce
    -0.85
     Trick
    -0.84
    trick
    -0.82
     commerce
    -0.82
    WireFormatLite
    -0.78
     COMMERCE
    -0.75
     tricks
    -0.73
    POSITIVE LOGITS
     dolayı
    0.44
     nele
    0.43
    Evaluation
    0.43
    handle
    0.42
    packages
    0.42
     konci
    0.42
     Evaluation
    0.42
    evaluation
    0.41
     initiator
    0.41
    ầu
    0.41
    Activations Density 2.186%

    No Known Activations