© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11064
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is talking about stuff they "have" and stuff that is "around"

    oai_token-act-pair · gemini-2.0-flash

    sitting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    MigrationBuilder
    -0.52
     principle
    -0.44
    aspectj
    -0.43
    ยว
    -0.42
    reportWebVitals
    -0.41
    EnableWeb
    -0.41
     rowspan
    -0.40
    greenrobot
    -0.40
    AFF
    -0.39
     suje
    -0.39
    POSITIVE LOGITS
     sitting
    2.30
     sit
    2.20
    sitting
    2.14
     Sitting
    2.08
    Sitting
    1.95
     sits
    1.94
     sat
    1.94
    Sit
    1.75
     Sit
    1.72
     lying
    1.66
    Activations Density 3.422%

    No Known Activations