© 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. 14756
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to getting a program to do something

    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
    labili
    -0.54
     것이다
    -0.47
    stateProvider
    -0.47
    
    -0.46
     ir
    -0.45
    ående
    -0.43
    PyTuple
    -0.42
    DataBind
    -0.42
    Locales
    -0.42
    onton
    -0.42
    POSITIVE LOGITS
    ResumeLayout
    0.68
    })$}
    0.67
    发表于
    0.65
     AssemblyCulture
    0.65
     surla
    0.65
     дописавши
    0.63
     kasarigan
    0.63
    RectangleBorder
    0.63
    مصادر
    0.61
     Gaul
    0.60
    Activations Density 5.390%

    No Known Activations