© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12680
    Prev
    Next
    INDEX
    Explanations

    text discussing alcohol, especially in terms of descriptions, recipes, and/or social contexts.

    oai_token-act-pair · gemini-2.0-flash

    alcohol or drinking

    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
     Alkohol
    -0.77
    Alcohol
    -0.75
     alcohol
    -0.75
     Alcohol
    -0.73
     wine
    -0.71
    alcohol
    -0.66
     Wine
    -0.65
     tobacco
    -0.64
    Wine
    -0.64
     brewery
    -0.64
    POSITIVE LOGITS
    IVEREF
    0.75
    rum
    0.69
     rum
    0.67
    bewerken
    0.60
     ویکی‌پدی
    0.59
     RUM
    0.54
    วา
    0.54
     Mez
    0.53
     spirits
    0.53
     kasarigan
    0.52
    Activations Density 3.631%

    No Known Activations