© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13022
    Prev
    Next
    INDEX
    Explanations

    phrases describing intention or direction

    oai_token-act-pair · gemini-2.0-flash

    directing attention/heading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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>
    -0.79
    ponses
    -0.77
    UTERS
    -0.59
     везе
    -0.56
    ibatis
    -0.55
     crdi
    -0.54
    />";
    -0.54
    CompleteListener
    -0.54
     ligiloj
    -0.53
    ksikon
    -0.53
    POSITIVE LOGITS
     Rely
    0.48
    ToBounds
    0.48
    setFrame
    0.47
    excellents
    0.46
     tunggal
    0.46
    RegressionTest
    0.45
    的一部分
    0.44
    linspace
    0.44
    [--
    0.43
     Signalez
    0.43
    Activations Density 1.804%

    No Known Activations