© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13362
    Prev
    Next
    INDEX
    Explanations

    the word "user" and related terms like "customer", "client", "friendly", "interface", and "use"

    oai_token-act-pair · gemini-2.0-flash

    user

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tagHelperRunner
    -0.91
    NameInMap
    -0.79
     للاسماء
    -0.79
     JpaRepository
    -0.73
     intptr
    -0.71
     NACIONAL
    -0.70
    ⓧ
    -0.69
     unknownFields
    -0.69
    dataclass
    -0.68
    ResumeLayout
    -0.66
    POSITIVE LOGITS
     friendly
    0.46
     هستیم
    0.44
    DeleteBehavior
    0.41
    friendly
    0.40
     experience
    0.38
    TableModel
    0.38
    orient
    0.38
    sizeCache
    0.38
    scriptcase
    0.37
    そうだ
    0.36
    Activations Density 0.546%

    No Known Activations