© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6415
    Prev
    Next
    INDEX
    Explanations

    the word "feel"

    oai_token-act-pair · gemini-2.0-flash

    feel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     feel
    -1.38
    feel
    -1.32
     Feel
    -1.02
    Feel
    -0.94
     sensazione
    -0.87
     wikipagina
    -0.79
    RectangleBorder
    -0.79
    feeling
    -0.78
    feels
    -0.78
     Houſe
    -0.77
    POSITIVE LOGITS
     referenties
    0.60
    euw
    0.59
    ,
    0.58
     in
    0.54
     earlier
    0.50
     ***!
    0.50
     within
    0.50
     Familienname
    0.49
     Hadid
    0.48
     out
    0.48
    Activations Density 1.304%

    No Known Activations