© 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. 13469
    Prev
    Next
    INDEX
    Explanations

    snippets of source code including array/matrix operations and assignments

    oai_token-act-pair · gemini-2.0-flash

    equals sign

    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
    ุ่ม
    -0.41
     UnityEngine
    -0.41
    util
    -0.40
     loja
    -0.36
    擎
    -0.36
    getMethod
    -0.35
     [*
    -0.35
     ch
    -0.35
    fuck
    -0.34
    iket
    -0.33
    POSITIVE LOGITS
     Италијани
    0.86
    EDEFAULT
    0.79
    Jeografia
    0.79
    +#+
    0.75
    posedge
    0.74
    脚注の使い方
    0.72
    __':
    0.71
     Biôgrafia
    0.71
    BibitemShut
    0.71
    DockStyle
    0.70
    Activations Density 0.996%

    No Known Activations