© 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. 13840
    Prev
    Next
    INDEX
    Explanations

    code snippets including variable names, ampersands, and other symbols found in programming languages

    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_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
    usepackage
    -0.49
    /***/
    -0.39
     AssemblyTitle
    -0.37
     relâche
    -0.36
     plan
    -0.35
    teau
    -0.35
    
    -0.34
    酔
    -0.33
     Bale
    -0.33
    Simply
    -0.33
    POSITIVE LOGITS
     estekak
    0.74
     Cæsar
    0.71
     Canaan
    0.69
     Teut
    0.67
    Abit
    0.66
    lccn
    0.65
     himſelf
    0.65
    úsqueda
    0.65
    papan
    0.64
    wnież
    0.63
    Activations Density 6.034%

    No Known Activations