© 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. 762
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by locations, times, or ordinal numbers relating to events

    oai_token-act-pair · gemini-2.0-flash

    international locations

    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
     createState
    -0.64
    CodeAttribute
    -0.61
    setVerticalGroup
    -0.59
    ScopeManager
    -0.59
    nalités
    -0.57
     NSCoder
    -0.56
    Cyfarwyddwr
    -0.52
     QName
    -0.49
    FirstResponder
    -0.49
    دانشنامهٔ
    -0.48
    POSITIVE LOGITS
     DriverManager
    0.55
     Turkmenistan
    0.54
     Tübingen
    0.54
     Regensburg
    0.53
     Kosovo
    0.52
    Fns
    0.51
     Kaisers
    0.50
     Städ
    0.50
     Armenia
    0.50
     New
    0.50
    Activations Density 2.884%

    No Known Activations