© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2353
    Prev
    Next
    INDEX
    Explanations

    words related to feelings, emotions, time, and experiences/occurrences

    oai_token-act-pair · gemini-2.0-flash

    Feelings/Emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ui
    -0.49
    те
    -0.48
    ri
    -0.46
    ,
    -0.46
    get
    -0.45
    am
    -0.44
    <bos>
    -0.44
    res
    -0.43
    le
    -0.42
    cor
    -0.42
    POSITIVE LOGITS
     itſelf
    0.99
     myſelf
    0.98
     againſt
    0.93
     becauſe
    0.92
     whoſe
    0.88
     Theſe
    0.86
     ſta
    0.85
    NUMX
    0.84
    expandindo
    0.84
     themſelves
    0.83
    Activations Density 11.342%

    No Known Activations