© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11594
    Prev
    Next
    INDEX
    Explanations

    tokens that appear very frequently, but also appear next to personal information, especially in the first passage provided

    oai_token-act-pair · gemini-2.0-flash

    user contact information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PreferredItem
    -0.56
     Strikes
    -0.55
     Pray
    -0.54
    UnitTesting
    -0.53
    saraba
    -0.52
    ্
    -0.52
     препратки
    -0.50
    Stacks
    -0.49
     Meld
    -0.46
    preventDefault
    -0.46
    POSITIVE LOGITS
    ThroughAttribute
    0.62
    viewDidLoad
    0.60
     Chwiliwch
    0.57
    ADELPHIA
    0.55
    hörigen
    0.55
     name
    0.55
     propOrder
    0.52
    Parcelize
    0.52
    HomeAsUpEnabled
    0.51
    VIAF
    0.50
    Activations Density 3.395%

    No Known Activations