© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 879
    Prev
    Next
    INDEX
    Explanations

    mentions of food and cooking either in the context of eating them, or making them.

    oai_token-act-pair · gemini-2.0-flash

    Food and recipes

    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
    extAlignment
    -0.65
    ftagPool
    -0.64
     kasarigan
    -0.57
     Reisedaten
    -0.56
    Cordialement
    -0.55
     fubject
    -0.54
     myſelf
    -0.54
     Portail
    -0.54
     againſt
    -0.52
    Portail
    -0.52
    POSITIVE LOGITS
    LookAnd
    0.54
    WebVitals
    0.49
    DockStyle
    0.48
     doInBackground
    0.45
    Климат
    0.45
     ffilmiau
    0.45
    nloa
    0.44
    :✨
    0.43
    etsk
    0.42
    Bromoform
    0.41
    Activations Density 1.662%

    No Known Activations