© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9478
    Prev
    Next
    INDEX
    Explanations

    job postings that include a location and discuss what the hospital is looking for

    oai_token-act-pair · gemini-2.0-flash

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     <<<<<<<<<<<<<<
    -0.83
    ImageContext
    -0.79
     дописавши
    -0.75
    GEBURTSDATUM
    -0.75
     propOrder
    -0.74
    IonicModule
    -0.73
     estekak
    -0.69
    QMetaType
    -0.68
    SharedDtor
    -0.68
    HasIndex
    -0.68
    POSITIVE LOGITS
     Answered
    0.45
    érêt
    0.44
    tease
    0.43
    니다
    0.43
    pompa
    0.42
    RODUCTION
    0.42
     okolí
    0.39
     natürlich
    0.38
    walde
    0.37
    ledes
    0.37
    Activations Density 0.056%

    No Known Activations