© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14188
    Prev
    Next
    INDEX
    Explanations

    code snippets containing function definitions and calls using identifier 'foo' and/or 'bar'

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    IndentedString
    -0.68
    PerformLayout
    -0.55
    interopRequire
    -0.54
     intptr
    -0.53
    photobucket
    -0.51
    IsContent
    -0.48
    商品説明
    -0.48
    onAttach
    -0.46
    awtextra
    -0.46
    XMLSchema
    -0.44
    POSITIVE LOGITS
    <bos>
    0.76
    giveness
    0.66
     photolibrary
    0.64
     échou
    0.60
     oaks
    0.60
     Orpheus
    0.58
     waterfall
    0.57
     Mian
    0.56
    égard
    0.56
     IndexPath
    0.56
    Activations Density 0.828%

    No Known Activations