© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10232
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are used in restaurant reviews and menus.

    oai_token-act-pair · gemini-2.0-flash

    Food-related

    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
     AssemblyCulture
    -0.88
    enderror
    -0.78
     autorytatywna
    -0.73
     مرئيه
    -0.63
    MockMvc
    -0.62
    CloseOperation
    -0.62
     виправивши
    -0.62
    Distribuzione
    -0.61
    astéro
    -0.61
     المعيارى
    -0.58
    POSITIVE LOGITS
    httphttps
    0.59
     tapas
    0.56
     Tapas
    0.49
     execution
    0.48
     entre
    0.46
    Tap
    0.46
    rceil
    0.45
     cured
    0.44
    execution
    0.44
     fondu
    0.44
    Activations Density 4.636%

    No Known Activations