© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13794
    Prev
    Next
    INDEX
    Explanations

    technical jargon, especially from mathematics and science

    oai_token-act-pair · gemini-2.0-flash

    Math and science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ็จ
    -0.47
     ŝ
    -0.47
    ROG
    -0.47
     roligt
    -0.47
    rog
    -0.46
     bakgrund
    -0.45
    stoke
    -0.45
    bose
    -0.45
    dolu
    -0.44
     fior
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.82
    RectangleBorder
    0.81
    DockStyle
    0.72
    NewReader
    0.69
    <bos>
    0.64
     doInBackground
    0.64
    ngrx
    0.63
    MLLoader
    0.60
    CodedInputStream
    0.60
    ℗
    0.59
    Activations Density 6.822%

    No Known Activations