© 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. 14854
    Prev
    Next
    INDEX
    Explanations

    java code filepaths

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    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
     Meksiku
    -0.56
     Man
    -0.46
     any
    -0.44
    engeti
    -0.44
     
    -0.43
    ViewFeatures
    -0.42
    Man
    -0.42
    chtenstein
    -0.41
    etcode
    -0.40
    chra
    -0.40
    POSITIVE LOGITS
    WriteTagHelper
    0.80
    ViewImports
    0.73
    TagMode
    0.72
    HtmlAttribute
    0.71
    はじめに
    0.69
     intptr
    0.69
     abandonné
    0.69
    featureID
    0.68
     getItemId
    0.68
    kuuta
    0.67
    Activations Density 3.057%

    No Known Activations