© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5341
    Prev
    Next
    INDEX
    Explanations

    words related to washing and antibodies.

    oai_token-act-pair · gemini-2.0-flash

    Washing/lab protocols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     wash
    -2.05
     washing
    -1.88
     washed
    -1.88
     washes
    -1.84
     Wash
    -1.83
    wash
    -1.79
    Wash
    -1.77
    Washing
    -1.66
    WASH
    -1.64
    washing
    -1.63
    POSITIVE LOGITS
     vivas
    0.44
    PageIndex
    0.42
    لاع
    0.38
     godz
    0.38
    getTop
    0.38
     compéti
    0.37
    μη
    0.37
    ChromeDriver
    0.36
     horaires
    0.36
     intValue
    0.36
    Activations Density 1.450%

    No Known Activations