© 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. 8149
    Prev
    Next
    INDEX
    Explanations

    words surrounding place names or government

    oai_token-act-pair · gemini-2.0-flash

    Islands

    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
     island
    -2.25
     Island
    -2.03
     ISLAND
    -2.02
    island
    -1.98
    Island
    -1.95
     islands
    -1.79
     islanders
    -1.73
     Islands
    -1.68
     ISLANDS
    -1.58
     Insel
    -1.45
    POSITIVE LOGITS
    DECREF
    0.50
    ścic
    0.45
     Sess
    0.45
     cere
    0.45
    FlowLayout
    0.44
    InitVars
    0.44
     Dortmund
    0.43
    دار
    0.43
     مواليد
    0.42
     Comercio
    0.41
    Activations Density 1.199%

    No Known Activations