© 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. 12961
    Prev
    Next
    INDEX
    Explanations

    words and phrases in formal writing

    oai_token-act-pair · gemini-2.0-flash

    change

    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
    XMLSchema
    -0.81
     חיצוניים
    -0.68
    InjectAttribute
    -0.67
    InstrumentedTest
    -0.65
    inaison
    -0.59
     unknownFields
    -0.59
     للاسماء
    -0.58
     ExecuteAsync
    -0.57
    ̍t
    -0.57
     يتيمه
    -0.56
    POSITIVE LOGITS
     change
    1.75
    change
    1.55
     Change
    1.48
    Change
    1.45
     CHANGE
    1.35
    CHANGE
    1.23
     cambio
    1.14
     changement
    0.89
     cambiamento
    0.87
     switch
    0.83
    Activations Density 16.063%

    No Known Activations