© 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. 12032
    Prev
    Next
    INDEX
    Explanations

    extended discussions about differing beliefs and values, especially regarding religion and social issues

    oai_token-act-pair · gemini-2.0-flash

    differences and imperfections

    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
     orejas
    -0.48
    лении
    -0.44
    liferay
    -0.42
     sois
    -0.42
    loroethene
    -0.42
     schie
    -0.42
     dår
    -0.42
    cives
    -0.42
    kuuta
    -0.41
    Pay
    -0.41
    POSITIVE LOGITS
     المعيارى
    0.74
    Legături
    0.67
    SharedCtor
    0.65
    addCriterion
    0.63
     wireType
    0.63
     springfox
    0.62
    <bos>
    0.60
    :✨
    0.60
     שוליים
    0.58
    OGND
    0.57
    Activations Density 6.180%

    No Known Activations