© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6624
    Prev
    Next
    INDEX
    Explanations

    words related to medical studies involving groups of patients

    oai_token-act-pair · gemini-2.0-flash

    No significant difference

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    RenderAtEndOf
    -0.84
    AutoScaleMode
    -0.82
     CreateTagHelper
    -0.81
    ########.
    -0.76
    httphttps
    -0.75
    PyExc
    -0.75
    sizeCache
    -0.74
    =$?
    -0.73
     ModelExpression
    -0.73
    CodeAttribute
    -0.72
    POSITIVE LOGITS
    chave
    0.50
    addContainerGap
    0.47
    ografija
    0.47
     differ
    0.44
     diferen
    0.44
    uvre
    0.44
    greater
    0.43
     sé
    0.43
     greater
    0.42
    ambil
    0.42
    Activations Density 6.260%

    No Known Activations