© 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. 12818
    Prev
    Next
    INDEX
    Explanations

    code blocks, particularly commenting syntax and mathematical notation within it

    oai_token-act-pair · gemini-2.0-flash

    Code/License Documentation

    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
    tagHelperRunner
    -0.95
    UrlResolution
    -0.71
     ostavi
    -0.69
    rawDesc
    -0.62
    kháu
    -0.62
     Signalez
    -0.60
    UnknownFieldSet
    -0.60
    ształ
    -0.60
    يكب
    -0.60
    esez
    -0.60
    POSITIVE LOGITS
    bewerken
    0.44
    CardHeader
    0.43
     Abp
    0.43
    detectChanges
    0.42
     MAE
    0.41
     wat
    0.40
    족
    0.40
    toBeDefined
    0.40
     utilisation
    0.40
    Dine
    0.40
    Activations Density 0.628%

    No Known Activations