© 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. 2649
    Prev
    Next
    INDEX
    Explanations

    code imports and annotations

    oai_token-act-pair · gemini-2.0-flash

    Java imports

    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
    +
    -0.53
    mær
    -0.53
    kring
    -0.48
    BASEPATH
    -0.48
     disponibilités
    -0.47
    acherous
    -0.46
     hữu
    -0.46
    '
    -0.45
    uspiel
    -0.44
    прочем
    -0.44
    POSITIVE LOGITS
    OGND
    0.90
     ویکی‌پدی
    0.81
    adpleegd
    0.80
     &___
    0.79
     cherchés
    0.79
     CreateTagHelper
    0.74
    tagHelperRunner
    0.72
    :✨
    0.69
     becauſe
    0.67
     protoimpl
    0.66
    Activations Density 1.075%

    No Known Activations