© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9814
    Prev
    Next
    INDEX
    Explanations

    words related to sugar

    oai_token-act-pair · gemini-2.0-flash

    sweet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     sweet
    -2.84
    sweet
    -2.75
    Sweet
    -2.64
     Sweet
    -2.64
     SWEET
    -2.45
     sweetness
    -2.14
     sweetest
    -2.13
    SWEET
    -2.11
     sweeter
    -2.05
     swee
    -1.76
    POSITIVE LOGITS
    ніципалі
    0.71
    aaral
    0.52
    Eksterne
    0.50
     كومونز
    0.49
    外部链接
    0.47
     alluminio
    0.47
    IntoConstraints
    0.47
    étricas
    0.47
     flesta
    0.46
    Vag
    0.46
    Activations Density 0.634%

    No Known Activations