© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10404
    Prev
    Next
    INDEX
    Explanations

    the start of blocks of code, based on indentation and comments

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ksikon
    -0.63
    Obrázky
    -0.62
    ContentAsync
    -0.60
    licazione
    -0.57
    Jereo
    -0.56
    dą
    -0.56
    ništ
    -0.55
     protoimpl
    -0.54
    ็จ
    -0.54
    PerformLayout
    -0.53
    POSITIVE LOGITS
    indest
    0.55
    setVerticalGroup
    0.54
     يتيمه
    0.53
    ↵↵
    0.52
    Pla
    0.50
     rowspan
    0.48
    Now
    0.47
    testng
    0.47
     numberOfRows
    0.45
    No
    0.43
    Activations Density 1.939%

    No Known Activations