© 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. 13132
    Prev
    Next
    INDEX
    Explanations

    the word "directed" and references to Greek mythology and certain employment actions

    oai_token-act-pair · gemini-2.0-flash

    directed

    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
    <bos>
    -2.09
    '
    -0.65
     Greek
    -0.62
    ’
    -0.56
    Greek
    -0.54
    I
    -0.51
    En
    -0.50
     AssemblyTitle
    -0.49
    R
    -0.48
    The
    -0.47
    POSITIVE LOGITS
    ViewFeatures
    0.81
     MainAxisSize
    0.79
     HasFactory
    0.71
    IntoConstraints
    0.71
    )<<
    0.66
    ricultural
    0.66
    secretary
    0.66
    ?
    0.65
    Bronnen
    0.64
    rowave
    0.63
    Activations Density 0.704%

    No Known Activations