© 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. 8350
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to drinking and social beverages, with connections to eating and being social.

    oai_token-act-pair · gemini-2.0-flash

    drinks

    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
     moulds
    -0.79
    sizeCache
    -0.76
    LookAnd
    -0.73
    Искәрмәләр
    -0.71
    onViewCreated
    -0.69
    Населення
    -0.69
     BoxFit
    -0.69
    fromCharCode
    -0.69
     שוליים
    -0.68
     Drink
    -0.67
    POSITIVE LOGITS
     Bang
    0.50
     domestic
    0.49
    té
    0.41
    éné
    0.41
    Bang
    0.41
     denn
    0.41
     su
    0.41
    arise
    0.40
     Z
    0.40
     pop
    0.40
    Activations Density 1.492%

    No Known Activations