© 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
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 176
    Prev
    Next
    INDEX
    Explanations

    uses of statistical formulas, specifically plugging values into them, along with data related to testing and training.

    oai_token-act-pair · gemini-2.0-flash

    coding functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     يتيمه
    -0.57
    ⓘ
    -0.56
    Suara
    -0.52
     bakgrund
    -0.50
    getMenuInflater
    -0.48
     obiec
    -0.46
     skydd
    -0.44
    AnchorStyles
    -0.44
     sidste
    -0.43
     abstrato
    -0.43
    POSITIVE LOGITS
    Geplaatst
    0.79
    XmlAccessType
    0.69
    ArgsConstructor
    0.67
     testSet
    0.62
     GenerationType
    0.62
    parametrize
    0.60
    Rujuakan
    0.59
    DeleteBehavior
    0.56
     IndexPath
    0.56
    quoi
    0.55
    Activations Density 1.886%

    No Known Activations