© 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. 10616
    Prev
    Next
    INDEX
    Explanations

    code or data structures like graphs, arrays and labels

    oai_token-act-pair · gemini-2.0-flash

    ---

    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
    évaluateur
    -0.77
    InjectAttribute
    -0.74
     pinulongan
    -0.72
     CreateTagHelper
    -0.71
     betweenstory
    -0.69
     الرياضيه
    -0.68
     CURIAM
    -0.64
     المتحدة
    -0.63
    RegressionTest
    -0.63
     createSlice
    -0.61
    POSITIVE LOGITS
    didSet
    0.50
    __*/
    0.49
     guardia
    0.47
     Compar
    0.44
    compar
    0.44
     comparison
    0.44
     COMPAR
    0.44
     compar
    0.44
    Comparison
    0.43
     compare
    0.43
    Activations Density 15.053%

    No Known Activations