© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12896
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to cyber security and data theft

    oai_token-act-pair · gemini-2.0-flash

    data breaches and hacking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AssemblyTitle
    -0.67
     Dati
    -0.60
     CYTHON
    -0.57
     متعلقه
    -0.57
     MaterialApp
    -0.54
    TypedDataSet
    -0.52
    Geplaatst
    -0.51
     calendriers
    -0.49
    ajoz
    -0.49
    ")));
    -0.48
    POSITIVE LOGITS
    뀜
    0.56
     sensitive
    0.55
    ubei
    0.52
    ValueStyle
    0.51
    Personendaten
    0.48
    Sortie
    0.48
    unsplash
    0.48
    ViewFeatures
    0.47
     consent
    0.47
     otomatig
    0.47
    Activations Density 5.502%

    No Known Activations