© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13573
    Prev
    Next
    INDEX
    Explanations

    apologetic phrases

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

    words and phrases apologizing for something

    oai_token-act-pair · gemini-2.0-flash

    Sorry

    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
    Conf
    -0.48
     sá
    -0.43
    pyx
    -0.43
    ONOM
    -0.42
     apologe
    -0.42
    tones
    -0.42
     ModelExpression
    -0.41
    iken
    -0.41
    paged
    -0.41
     kasarigan
    -0.41
    POSITIVE LOGITS
     الاطلاع
    0.74
     BorderRadius
    0.73
    новништво
    0.67
    MENAFN
    0.66
    mybatisplus
    0.64
    хьтан
    0.62
    fjspx
    0.61
     for
    0.60
     but
    0.60
    envolvimento
    0.58
    Activations Density 3.141%

    No Known Activations