© 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. 3333
    Prev
    Next
    INDEX
    Explanations

    names, dates, locations of people and events

    oai_token-act-pair · gemini-2.0-flash

    biographies

    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
     live
    -0.88
    Live
    -0.71
     lived
    -0.70
    live
    -0.69
     Live
    -0.67
    SharedDtor
    -0.66
     Lived
    -0.66
    LIVE
    -0.65
     LIVE
    -0.64
     ComVisible
    -0.63
    POSITIVE LOGITS
    ptonshire
    0.51
     insuffisamment
    0.50
    abestanden
    0.47
    StateToProps
    0.45
    %@",
    0.44
    rrggbb
    0.43
    past
    0.43
    IEnumerator
    0.42
    WebElementEntity
    0.42
    COMB
    0.42
    Activations Density 11.210%

    No Known Activations