© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11352
    Prev
    Next
    INDEX
    Explanations

    references to locations, specifically Schleswig-Holstein and place names within Finland

    oai_token-act-pair · gemini-2.0-flash

    Multilingual, technical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    principalTable
    -0.71
    Personensuche
    -0.65
    ApplicationTests
    -0.59
    /</
    -0.59
    .)}
    -0.56
    "}")
    -0.55
    StoreMessageInfo
    -0.54
    сылкі
    -0.54
     EconPapers
    -0.54
    }(),
    -0.52
    POSITIVE LOGITS
     se
    0.62
    WithIOException
    0.48
     RouterModule
    0.47
    ναν
    0.44
     kiv
    0.44
    тябрь
    0.43
     PopupWindow
    0.43
    UAGES
    0.43
     feed
    0.42
    WebServlet
    0.41
    Activations Density 0.211%

    No Known Activations