© 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. 6499
    Prev
    Next
    INDEX
    Explanations

    words related to UV light and optics

    oai_token-act-pair · gemini-2.0-flash

    terms related to killing or death

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

    UV radiation and light

    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
    脚注の使い方
    -0.59
     Espacio
    -0.56
    //
    -0.56
     jsPsych
    -0.56
     Indra
    -0.54
     Asbury
    -0.54
     Havel
    -0.54
    ècie
    -0.54
     Deccan
    -0.54
     crucible
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    0.71
     ger
    0.66
    WriteBarrier
    0.60
     lámparas
    0.57
     killing
    0.57
    Killing
    0.52
     Killing
    0.50
    ger
    0.49
     tué
    0.48
     kill
    0.48
    Activations Density 2.304%

    No Known Activations