© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10076
    Prev
    Next
    INDEX
    Explanations

    legal and political terms and entities related to immigration and status in a country, as well as related code and text in other languages.

    oai_token-act-pair · gemini-2.0-flash

    Code and unstructured data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     avoient
    -1.41
     varandra
    -1.39
     étoient
    -1.35
     stället
    -1.34
     étoit
    -1.32
     auroit
    -1.32
     enfans
    -1.31
     feroit
    -1.29
     pitié
    -1.26
     dieux
    -1.24
    POSITIVE LOGITS
    of
    0.21
    by
    0.16
    <eos>
    0.16
    on
    0.16
    he
    0.15
    one
    0.14
    ones
    0.14
    ,
    0.14
    ↵↵
    0.13
    if
    0.13
    Activations Density 1.204%

    No Known Activations