© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4013
    Prev
    Next
    INDEX
    Explanations

    terms related to internet security

    oai_token-act-pair · gemini-2.0-flash

    Computer networking and security

    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
    ThroughAttribute
    -0.79
    esez
    -0.62
    Gweler
    -0.54
    RegistryLite
    -0.53
    Spoljašnje
    -0.52
    NOPQRST
    -0.51
    Хьажоргаш
    -0.50
    NgModule
    -0.50
     ivelany
    -0.50
    Geplaatst
    -0.49
    POSITIVE LOGITS
     hand
    0.54
     Alvarado
    0.53
    vieja
    0.52
     Hand
    0.50
    Guerra
    0.50
    WICK
    0.49
    rinhos
    0.47
    Infin
    0.47
     Infin
    0.47
     pró
    0.47
    Activations Density 4.584%

    No Known Activations