© 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. 10374
    Prev
    Next
    INDEX
    Explanations

    the word 'supported'

    oai_token-act-pair · gemini-2.0-flash

    code/testing

    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
    aziland
    -0.61
     kasarigan
    -0.52
     classification
    -0.51
     مشين
    -0.50
     كومونز
    -0.50
    /$',
    -0.50
     jspb
    -0.46
    dafrika
    -0.45
     category
    -0.44
    ParallelGroup
    -0.44
    POSITIVE LOGITS
    LLocation
    0.64
    webElementXpaths
    0.60
    RoleName
    0.59
     initComponents
    0.57
     belieb
    0.56
     MATHEMATICAL
    0.55
    ArgumentParser
    0.54
    Espèce
    0.54
    tagHelper
    0.51
    InputTagHelper
    0.51
    Activations Density 23.864%

    No Known Activations