© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9645
    Prev
    Next
    INDEX
    Explanations

    words describing posture and body support, especially in a medical context.

    oai_token-act-pair · gemini-2.0-flash

    Body position/physical therapy

    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
    FXML
    -0.61
    ToBounds
    -0.59
    ReusableCell
    -0.57
    Mockito
    -0.56
     VIDEOTAPE
    -0.52
    MENAFN
    -0.52
     للمعارف
    -0.52
    LookAnd
    -0.52
    Captor
    -0.52
    ."]
    -0.51
    POSITIVE LOGITS
    :✨
    0.54
    skri
    0.50
     Paglinawan
    0.48
     esterni
    0.48
    matchCondition
    0.47
    expandindo
    0.46
    acyjny
    0.45
    paksa
    0.45
    flexGrow
    0.45
    nocześnie
    0.44
    Activations Density 1.002%

    No Known Activations