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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7340
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to product returns

    oai_token-act-pair · gemini-2.0-flash

    terms related to products and returns

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

    Foreign words

    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
     الدولى
    -0.56
    anti
    -0.50
     alfo
    -0.49
    ("$.
    -0.48
     thefe
    -0.48
     '-';
    -0.47
     Bioaccumulative
    -0.47
    лыша
    -0.46
    hara
    -0.46
    reciate
    -0.46
    POSITIVE LOGITS
     الحره
    0.86
     виправивши
    0.83
    expandindo
    0.81
     كومونز
    0.67
    __':
    0.63
     referenties
    0.62
     products
    0.60
    новништво
    0.59
    原始内容存档于
    0.58
     goods
    0.57
    Activations Density 1.980%

    No Known Activations