© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4665
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations, particularly related to geometry and trigonometry

    oai_token-act-pair · gemini-2.0-flash

    Math constants/functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Attending
    -0.76
    attend
    -0.73
     attending
    -0.71
     sumpay
    -0.71
     attend
    -0.71
     Attendance
    -0.69
     attendance
    -0.68
     Attend
    -0.67
     متعلقه
    -0.67
    Attend
    -0.66
    POSITIVE LOGITS
    PreferredItem
    0.53
    <bos>
    0.52
     Référence
    0.49
    FileOutputStream
    0.42
    enumi
    0.42
    las
    0.41
    WriteTagHelper
    0.40
    ]=>
    0.40
    roek
    0.40
    resizingMask
    0.40
    Activations Density 0.950%

    No Known Activations