© 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. 10235
    Prev
    Next
    INDEX
    Explanations

    words that occur in restaurant reviews

    oai_token-act-pair · gemini-2.0-flash

    Restaurant reviews, crowded places

    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
    AccessorTable
    -0.50
     hänen
    -0.50
    šanās
    -0.49
    ken
    -0.46
     Erzb
    -0.46
     للمعارف
    -0.45
     ardu
    -0.45
    ValueStyle
    -0.44
    ism
    -0.44
    Selectable
    -0.44
    POSITIVE LOGITS
    PhysRevD
    0.63
    parsedMessage
    0.59
    AFFIRMED
    0.57
    OrBuilder
    0.57
    LabelTagHelper
    0.57
    MockBean
    0.56
     touristique
    0.56
    BeginContext
    0.56
     Riproduzione
    0.55
     חיצוניים
    0.55
    Activations Density 1.557%

    No Known Activations