© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8043
    Prev
    Next
    INDEX
    Explanations

    restaurant and food reviews.

    oai_token-act-pair · gemini-2.0-flash

    food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     referenties
    -0.57
    pédie
    -0.52
    ToBounds
    -0.51
    kab
    -0.49
    Slf
    -0.48
    setupUi
    -0.48
     catapult
    -0.48
    Geplaatst
    -0.45
     kasarigan
    -0.45
     Le
    -0.45
    POSITIVE LOGITS
    FormTagHelper
    0.74
    kuuta
    0.53
    发表于
    0.53
     italienne
    0.53
     Wiktionnaire
    0.52
    NullCheck
    0.49
    ΟΣ
    0.48
    ่น
    0.48
     Roja
    0.48
    Története
    0.48
    Activations Density 5.934%

    No Known Activations