© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7424
    Prev
    Next
    INDEX
    Explanations

    mentions of Cyprus

    np_token-act-pair-logits · gpt-4o-mini

    geographic place names

    oai_token-act-pair · gemini-2.0-flash

    Cyprus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Erstellt
    -0.79
    parsedMessage
    -0.76
    IsMutable
    -0.75
     Exacts
    -0.67
    contentLoaded
    -0.66
     iprot
    -0.66
    tagHelperRunner
    -0.65
    رشف
    -0.65
     חיצוניים
    -0.64
     متعلقه
    -0.64
    POSITIVE LOGITS
    rrggbb
    0.52
    WarningLevel
    0.48
     ma
    0.47
    psack
    0.47
     Tam
    0.47
     tri
    0.46
     Republik
    0.45
     Mar
    0.45
    führt
    0.45
    fhir
    0.44
    Activations Density 0.721%

    No Known Activations