© 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. 4630
    Prev
    Next
    INDEX
    Explanations

    pronouns

    oai_token-act-pair · gemini-2.0-flash

    people

    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
     injective
    -0.67
     ingrat
    -0.66
     Yugoslavia
    -0.63
     mitral
    -0.62
    harp
    -0.61
     Neander
    -0.61
     Situations
    -0.60
     orthogonal
    -0.60
     Constantinople
    -0.59
     traitors
    -0.59
    POSITIVE LOGITS
    <bos>
    1.22
    $.}
    0.67
     because
    0.66
     AssemblyTitle
    0.66
     he
    0.57
    __':
    0.55
    >());
    0.54
    Autoritní
    0.52
     the
    0.52
    /}.
    0.51
    Activations Density 1.041%

    No Known Activations