© 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. 6551
    Prev
    Next
    INDEX
    Explanations

    square root mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    sqrt

    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
    <bos>
    -2.86
    sqrt
    -1.09
    qrt
    -0.89
     sqrt
    -0.88
    '
    -0.85
    ’
    -0.69
    √
    -0.66
    "
    -0.65
    -
    -0.62
    Sqrt
    -0.58
    POSITIVE LOGITS
    haviour
    0.59
    ousands
    0.58
     continuant
    0.57
     Bumper
    0.57
     Assignee
    0.56
    ionali
    0.55
     يتيمه
    0.54
    MLLoader
    0.54
     trast
    0.54
    havior
    0.54
    Activations Density 0.339%

    No Known Activations