© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15629
    Prev
    Next
    INDEX
    Explanations

    words related to scientific research or medicine

    oai_token-act-pair · gemini-2.0-flash

    variations of "in"

    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
     involved
    -2.08
    involved
    -1.88
     involve
    -1.88
     Involved
    -1.82
     involving
    -1.66
     INVOLVED
    -1.66
     involves
    -1.64
     involvement
    -1.53
     involucra
    -1.52
     Involvement
    -1.46
    POSITIVE LOGITS
     In
    0.81
    IN
    0.79
    in
    0.78
    In
    0.71
     IN
    0.64
    イン
    0.54
    rest
    0.52
    ynch
    0.49
     imp
    0.47
     rest
    0.46
    Activations Density 4.491%

    No Known Activations