© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4319
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to liquids and being surrounded

    oai_token-act-pair · gemini-2.0-flash

    Something being enclosed

    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
    find
    -0.70
    try
    -0.61
    this
    -0.61
    var
    -0.60
    #
    -0.59
    return
    -0.59
    y
    -0.59
    if
    -0.59
     scom
    -0.57
    __
    -0.57
    POSITIVE LOGITS
    ^(@)
    0.96
     photolibrary
    0.93
    ConstraintMaker
    0.91
    SBATCH
    0.91
    thenReturn
    0.90
    bibfield
    0.88
    BibitemShut
    0.88
    leſs
    0.86
    servername
    0.85
    mybatisplus
    0.84
    Activations Density 1.069%

    No Known Activations