© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11935
    Prev
    Next
    INDEX
    Explanations

    words that express negation or issues

    oai_token-act-pair · gemini-2.0-flash

    Negative impact/consequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     improve
    -0.92
     benefits
    -0.92
     benefit
    -0.91
     benefited
    -0.89
     improving
    -0.88
     improved
    -0.88
     benefitted
    -0.88
     Improves
    -0.86
     improvement
    -0.85
     improves
    -0.85
    POSITIVE LOGITS
    Vidite
    0.65
    참고
    0.57
     TextInputType
    0.50
     ddelweddau
    0.48
     دیکھیے
    0.46
     POTENTIAL
    0.46
    quiti
    0.46
    PRNewswire
    0.46
    thinkable
    0.45
    createCanvas
    0.45
    Activations Density 5.349%

    No Known Activations