© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5015
    Prev
    Next
    INDEX
    Explanations

    the word "wish" and sometimes "desires."

    oai_token-act-pair · gemini-2.0-flash

    wish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     wish
    -2.42
     wished
    -2.05
     wishes
    -1.96
     Wish
    -1.91
    wish
    -1.90
     wishing
    -1.87
    Wish
    -1.82
     WISH
    -1.73
    <bos>
    -1.52
     Wishing
    -1.41
    POSITIVE LOGITS
     المعيارى
    0.75
    ValueStyle
    0.73
    Билгалдахарш
    0.72
     يتيمه
    0.69
    fromnode
    0.66
    Hochspringen
    0.63
    ReusableCell
    0.62
    omyces
    0.59
    mpty
    0.57
    EVP
    0.57
    Activations Density 0.978%

    No Known Activations