© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10330
    Prev
    Next
    INDEX
    Explanations

    mentions of food, especially sandwiches and ingredients

    oai_token-act-pair · gemini-2.0-flash

    food and sandwiches

    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
    AddTagHelper
    -1.12
    хьтан
    -0.84
     ComVisible
    -0.75
     الرياضيه
    -0.75
    клопе
    -0.70
     AssemblyCulture
    -0.67
     Exactos
    -0.67
     arşivlendi
    -0.67
    CloseOperation
    -0.66
    getSeconds
    -0.65
    POSITIVE LOGITS
    Vidite
    0.49
     wrap
    0.49
     sost
    0.47
    cera
    0.45
     apro
    0.45
    agie
    0.43
     Wrap
    0.42
    acen
    0.42
    xty
    0.41
    auen
    0.41
    Activations Density 0.790%

    No Known Activations