© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4826
    Prev
    Next
    INDEX
    Explanations

    a variety of named entities, locations, dates, political terms, or technology terms.

    oai_token-act-pair · gemini-2.0-flash

    say comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    σθαι
    -0.66
    findpost
    -0.65
    Източници
    -0.65
    ImageField
    -0.63
    ؛
    -0.62
     autorytatywna
    -0.61
    Бележки
    -0.60
    mær
    -0.59
    ApplicationTests
    -0.58
    」，
    -0.57
    POSITIVE LOGITS
    ,
    2.50
    OGND
    0.67
    AddTagHelper
    0.45
    numerusform
    0.43
    》.
    0.41
    transQ
    0.38
    іга
    0.34
    satunya
    0.33
    ).-
    0.33
    chitis
    0.32
    Activations Density 9.084%

    No Known Activations