© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4306
    Prev
    Next
    INDEX
    Explanations

    symbols and descriptions of figures and diagrams that would appear in a scientific paper

    oai_token-act-pair · gemini-2.0-flash

    lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    tagHelperRunner
    -0.76
     referenties
    -0.75
    mtrl
    -0.72
     comparaison
    -0.69
    StoryboardSegue
    -0.66
     Lightboxes
    -0.66
    webElementXpaths
    -0.66
     '\\;'
    -0.66
    IndentedString
    -0.65
    AccessorTable
    -0.64
    POSITIVE LOGITS
     toegang
    0.51
     menyus
    0.45
     setError
    0.45
     gospel
    0.44
     labios
    0.43
    sscanf
    0.43
     jobbet
    0.42
    CodeAttribute
    0.42
     tâche
    0.42
    ンテ
    0.41
    Activations Density 0.457%

    No Known Activations