© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1055
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and notation

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ſeveral
    -0.85
     leaſt
    -0.82
     themſelves
    -0.78
     fhew
    -0.77
     Reſ
    -0.76
     becauſe
    -0.72
     whoſe
    -0.71
     termica
    -0.69
     sauvages
    -0.69
     réguli
    -0.69
    POSITIVE LOGITS
    __':
    0.80
     ال
    0.68
    }{*}{
    0.68
    ?>">
    0.68
    );?>
    0.67
     ?>">
    0.67
    WEBPACK
    0.66
     }?>
    0.66
    :][
    0.64
    liferay
    0.64
    Activations Density 2.986%

    No Known Activations