© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14957
    Prev
    Next
    INDEX
    Explanations

    phrases in scientific papers that describe the setup of an experiment or analysis

    oai_token-act-pair · 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
     Paglinawan
    -0.90
    Portály
    -0.75
    ]--;
    -0.74
     חיצוניים
    -0.73
    Спољашње
    -0.72
     GenerationType
    -0.69
     CreateTagHelper
    -0.69
     propOrder
    -0.68
     Observer
    -0.66
     depositphotos
    -0.66
    POSITIVE LOGITS
     model
    0.51
    model
    0.49
    воря
    0.41
    })`
    0.40
    amodel
    0.39
    モデル
    0.38
    avanaugh
    0.38
     Model
    0.38
    Model
    0.35
     means
    0.34
    Activations Density 3.942%

    No Known Activations