© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13494
    Prev
    Next
    INDEX
    Explanations

    scientific or medical terminology, especially related to cell types and their activity states

    oai_token-act-pair · gemini-2.0-flash

    positive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    躇
    -0.56
    erequisites
    -0.53
     lasso
    -0.52
    UnifiedTopology
    -0.51
    toral
    -0.51
    romp
    -0.51
    arraycopy
    -0.51
    ServiceTest
    -0.51
     CascadeType
    -0.50
    correct
    -0.50
    POSITIVE LOGITS
    новниш
    0.75
    Initializable
    0.74
    TagMode
    0.68
    queryInterface
    0.58
     houſe
    0.58
    évaluateur
    0.58
     tasche
    0.57
    glBindBuffer
    0.53
     pleaſure
    0.52
    Chham
    0.52
    Activations Density 4.474%

    No Known Activations