© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10268
    Prev
    Next
    INDEX
    Explanations

    the number 2, especially when it is adjacent to other numbers, and also words for numbers

    oai_token-act-pair · gemini-2.0-flash

    2

    np_max-act · gemini-2.0-flash

    2

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Paglinawan
    -0.93
     متعلقه
    -0.81
     فريبيس
    -0.80
     betweenstory
    -0.77
    protoimpl
    -0.72
     AdapterView
    -0.71
    UserScript
    -0.71
    +:+
    -0.70
    tvguidetime
    -0.69
     violins
    -0.69
    POSITIVE LOGITS
    <bos>
    1.34
     two
    0.69
     
    0.63
    Two
    0.62
     The
    0.61
    The
    0.60
     Two
    0.60
     a
    0.59
     to
    0.58
    Y
    0.57
    Activations Density 0.574%

    No Known Activations