© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4911
    Prev
    Next
    INDEX
    Explanations

    the word "recommendation" and related terms.

    oai_token-act-pair · gemini-2.0-flash

    recommendations and guidelines

    np_token-act-pair-logits · gpt-4o-mini

    recommendation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     recommendation
    -2.84
     recommended
    -2.81
     recommend
    -2.75
     recommendations
    -2.67
     recommending
    -2.61
     recommends
    -2.53
     Recommendation
    -2.50
     Recommendations
    -2.39
     Recommended
    -2.38
     Recommend
    -2.34
    POSITIVE LOGITS
     nationaux
    0.65
    BASELINE
    0.61
     للاسماء
    0.56
     préc
    0.54
     TextAlign
    0.52
     hôte
    0.51
    følgelig
    0.50
     urbain
    0.50
    illige
    0.49
    uguetes
    0.49
    Activations Density 1.099%

    No Known Activations