© 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. 15507
    Prev
    Next
    INDEX
    Explanations

    Latex, PHP, and C++ code snippets

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     onPostExecute
    -0.76
    GeoNames
    -0.67
    Geplaatst
    -0.67
    Chham
    -0.66
    ándolos
    -0.62
    apkamer
    -0.61
    ériques
    -0.61
    SourceChecksum
    -0.60
    TagHelpers
    -0.60
    XmlAccessorType
    -0.60
    POSITIVE LOGITS
     سكانية
    0.59
     &___
    0.54
     politiet
    0.51
    Життєпис
    0.51
     Gump
    0.49
     Permalink
    0.49
     Universitaria
    0.47
    SupportActionBar
    0.46
     Pavement
    0.46
     polig
    0.45
    Activations Density 8.803%

    No Known Activations