© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6491
    Prev
    Next
    INDEX
    Explanations

    the word "so" and phrases of comparison

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ########.
    -0.51
     Audiodateien
    -0.50
    ÁG
    -0.49
    raven
    -0.47
     Pays
    -0.46
     Sol
    -0.46
     прошло
    -0.45
     referenties
    -0.45
     More
    -0.45
     Parti
    -0.44
    POSITIVE LOGITS
    mybatisplus
    0.91
    awtextra
    0.72
    ArgsConstructor
    0.60
    Rüyada
    0.57
    AddHtmlAttribute
    0.56
    sendRedirect
    0.56
    SequentialGroup
    0.54
    othed
    0.54
    sizeCache
    0.53
     składa
    0.53
    Activations Density 0.562%

    No Known Activations