© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6323
    Prev
    Next
    INDEX
    Explanations

    words that indicate quantity or comparison and negation, especially when discussing statistical differences in research.

    oai_token-act-pair · gemini-2.0-flash

    differences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ⓧ
    -1.22
     myſelf
    -1.18
     Jefus
    -1.16
     itſelf
    -1.15
     Chriftian
    -1.12
     Majefty
    -1.11
     purpoſe
    -1.10
     themſelves
    -1.08
    دانشنامهٔ
    -1.05
     houſe
    -1.05
    POSITIVE LOGITS
     variations
    0.57
     differences
    0.57
     regional
    0.54
     discrepancies
    0.49
     change
    0.47
     changes
    0.47
     inconsistencies
    0.47
     ver
    0.46
     g
    0.46
     deviations
    0.45
    Activations Density 4.489%

    No Known Activations