© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4342
    Prev
    Next
    INDEX
    Explanations

    words related to meat and food contamination

    oai_token-act-pair · gemini-2.0-flash

    Meats and cooking

    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
     meat
    -1.77
     Meat
    -1.69
    Meat
    -1.64
     MEAT
    -1.55
    meat
    -1.52
     meats
    -1.30
     Beef
    -1.26
    肉
    -1.23
     beef
    -1.17
    Beef
    -1.15
    POSITIVE LOGITS
    CloseOperation
    0.70
     كومونز
    0.59
    paraíso
    0.52
    Билгалдахарш
    0.51
    جغرافيا
    0.49
     jsPsych
    0.48
    IFS
    0.47
    oughlin
    0.47
     HasFactory
    0.47
     angebra
    0.45
    Activations Density 0.991%

    No Known Activations