© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5443
    Prev
    Next
    INDEX
    Explanations

    the word "as," along with some legal jargon and also words regarding official processes.

    oai_token-act-pair · gemini-2.0-flash

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Audiodateien
    -0.67
    awtextra
    -0.66
    Revenir
    -0.59
    исленность
    -0.59
    setVerticalGroup
    -0.59
    ParallelGroup
    -0.57
    Nå
    -0.57
    はじめに
    -0.56
    łki
    -0.54
    Hochspringen
    -0.54
    POSITIVE LOGITS
     to
    2.77
     να
    1.16
    to
    1.09
     чтобы
    0.93
     To
    0.82
    ที่จะ
    0.78
     לה
    0.75
     aufzu
    0.75
    DataTo
    0.75
     abzu
    0.74
    Activations Density 20.030%

    No Known Activations