© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6291
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings and international relations

    oai_token-act-pair · gemini-2.0-flash

    War, refugees, and displacement

    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
    twimg
    -0.53
     Мексичка
    -0.53
    NullCheck
    -0.52
    ilich
    -0.49
    SHIRE
    -0.48
    classID
    -0.47
    EDEFAULT
    -0.46
     Middlesex
    -0.46
     torchvision
    -0.46
     correctes
    -0.46
    POSITIVE LOGITS
    Rhestr
    0.70
    providedIn
    0.56
    URLException
    0.52
     ligiloj
    0.52
    PreAuthorize
    0.49
    CreateMap
    0.48
     held
    0.47
    }))
    0.47
    setViewName
    0.47
     subject
    0.47
    Activations Density 8.792%

    No Known Activations