© 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. 13518
    Prev
    Next
    INDEX
    Explanations

    Java code snippets containing variable declarations and programming keywords

    oai_token-act-pair · gemini-2.0-flash

    int

    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
     int
    -0.64
    Tikang
    -0.63
     cherchés
    -0.60
     nahilalakip
    -0.60
    Geplaatst
    -0.57
    <bos>
    -0.56
    sizeCache
    -0.54
    цезда
    -0.53
    Risultati
    -0.52
    LikeLiked
    -0.51
    POSITIVE LOGITS
     collectif
    0.57
    存于互联网档案馆
    0.56
    tagHelperRunner
    0.53
    ]")]
    0.49
    RunAsync
    0.49
    utiva
    0.48
     passi
    0.48
    quial
    0.47
     esterni
    0.47
     DUT
    0.47
    Activations Density 2.968%

    No Known Activations