© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11846
    Prev
    Next
    INDEX
    Explanations

    language indicating that something is unexplained or interesting in a surprising way

    oai_token-act-pair · gemini-2.0-flash

    because

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     parseFrom
    -0.66
    abestanden
    -0.64
    makeConstraints
    -0.58
     bezeichneter
    -0.58
     дописавши
    -0.58
    RequestQueue
    -0.57
    propTypes
    -0.57
    rungsseite
    -0.56
     vastaan
    -0.54
    thâu
    -0.52
    POSITIVE LOGITS
     because
    1.91
     since
    1.79
    because
    1.72
     karena
    1.59
    since
    1.59
     porque
    1.55
     поскольку
    1.48
     poiché
    1.45
    Because
    1.43
     Because
    1.41
    Activations Density 4.316%

    No Known Activations