© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8010
    Prev
    Next
    INDEX
    Explanations

    This neuron is recognizing words within a German sentence, and the words it activates on would be helpful when trying to understand the meaning of someone's words or actions

    oai_token-act-pair · gemini-2.0-flash

    man

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     الاطلاع
    -0.57
    ্ষ
    -0.54
    ample
    -0.54
    原始内容存档于
    -0.51
     Dr
    -0.50
    éenne
    -0.50
     đáp
    -0.49
    деми
    -0.49
    shadowOpacity
    -0.49
     Z
    -0.48
    POSITIVE LOGITS
    <bos>
    0.69
    ttino
    0.63
    GEBURTSDATUM
    0.58
    #
    0.56
    ########.
    0.56
    eleste
    0.55
    icace
    0.54
     occasionally
    0.53
    cjon
    0.52
    ictus
    0.52
    Activations Density 0.298%

    No Known Activations