© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11953
    Prev
    Next
    INDEX
    Explanations

    the word "thing" and variations of "foo" and "bar" used as code examples

    oai_token-act-pair · gemini-2.0-flash

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ViewFeatures
    -0.57
    __":
    -0.54
     Grafton
    -0.51
     CERN
    -0.49
     pañ
    -0.49
    jerc
    -0.48
     invariance
    -0.48
     eukaryotic
    -0.47
    ValueStyle
    -0.47
     yonder
    -0.47
    POSITIVE LOGITS
    ⓧ
    0.63
     يتيمه
    0.61
    Референце
    0.58
    RegistryLite
    0.56
    хьтан
    0.55
    DJANGO
    0.54
     StatelessWidget
    0.54
    quiera
    0.54
    وفاته
    0.53
     ExecuteAsync
    0.52
    Activations Density 3.002%

    No Known Activations