© 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. 12202
    Prev
    Next
    INDEX
    Explanations

    the word "aware".

    oai_token-act-pair · gemini-2.0-flash

    aware

    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
     aware
    -0.72
    <bos>
    -0.69
    aware
    -0.64
    Enabled
    -0.62
    enabled
    -0.55
    Aware
    -0.52
    ENABLED
    -0.51
    новен
    -0.49
    /**
    -0.47
     ند
    -0.46
    POSITIVE LOGITS
    ContentAsync
    0.88
     greateſt
    0.88
    RegressionTest
    0.88
     himſelf
    0.86
     Diſ
    0.84
     Monfieur
    0.82
     pleaſure
    0.77
     becauſe
    0.77
    istoitu
    0.76
     leaſt
    0.75
    Activations Density 0.628%

    No Known Activations