© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11621
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, percentages, and structural data (such as tables).

    oai_token-act-pair · gemini-2.0-flash

    Math equations and fractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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>
    -0.61
    onius
    -0.57
     jsPsych
    -0.53
    issauga
    -0.52
    chum
    -0.51
    onik
    -0.50
    NUMX
    -0.47
    zym
    -0.47
    ety
    -0.47
    saraba
    -0.46
    POSITIVE LOGITS
    دانشنامهٔ
    0.83
    expandindo
    0.78
    UnsafeEnabled
    0.75
    ValueStyle
    0.73
    windowFixed
    0.69
     Signalez
    0.68
    Jeografia
    0.68
     المعيارى
    0.67
    Trama
    0.64
     utafitiHapana
    0.64
    Activations Density 0.459%

    No Known Activations