© 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. 1968
    Prev
    Next
    INDEX
    Explanations

    sentences describing computer security processes and tools

    oai_token-act-pair · gemini-2.0-flash

    cybersecurity

    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
     defStyle
    -0.69
    webElementGuid
    -0.67
    ContentAsync
    -0.66
    LookAnd
    -0.60
     déc
    -0.57
    rxjs
    -0.56
    ("../../
    -0.55
     ReactDOM
    -0.55
     ویکی‌پدیا
    -0.54
    Välislingid
    -0.54
    POSITIVE LOGITS
     ролях
    0.48
     définiti
    0.48
    transparency
    0.46
    省市镇
    0.45
    stealth
    0.45
    trailing
    0.45
    vezető
    0.44
     mourir
    0.44
     uppgifter
    0.44
     voici
    0.43
    Activations Density 2.664%

    No Known Activations