© 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. 15771
    Prev
    Next
    INDEX
    Explanations

    words related to food and food preparation, especially processed food

    oai_token-act-pair · gemini-2.0-flash

    smoking and curing

    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
    HasForeignKey
    -0.53
     useState
    -0.48
    TP
    -0.46
    ladung
    -0.46
    laquo
    -0.46
    AlterField
    -0.45
     Pons
    -0.45
    djangoproject
    -0.44
    ark
    -0.44
    cyklopedia
    -0.43
    POSITIVE LOGITS
     smoke
    0.66
     smoker
    0.65
     Informações
    0.64
    smoke
    0.62
     cure
    0.61
     Smoke
    0.60
     glaze
    0.59
     smoked
    0.59
    cure
    0.58
     JADX
    0.58
    Activations Density 1.412%

    No Known Activations