© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7464
    Prev
    Next
    INDEX
    Explanations

    words related to US foreign policy in Central America in the 1980s

    oai_token-act-pair · gemini-2.0-flash

    News and current events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     مشين
    -0.84
    NameInMap
    -0.82
     AssemblyCulture
    -0.75
    Portale
    -0.71
     esternos
    -0.69
    دانشنامهٔ
    -0.64
    interopRequire
    -0.63
    ScopeManager
    -0.63
    thâu
    -0.63
    XMLSchema
    -0.62
    POSITIVE LOGITS
    sika
    0.51
    $'
    0.47
     Putih
    0.46
     "}";
    0.46
     employes
    0.46
     countryman
    0.45
     Rocca
    0.45
    ,:]
    0.45
     Achille
    0.45
    ]++;
    0.44
    Activations Density 22.560%

    No Known Activations