© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8727
    Prev
    Next
    INDEX
    Explanations

    computer-programming-related terms or code snippets

    oai_token-act-pair · gemini-2.0-flash

    words related to programming constructs or frameworks

    np_token-act-pair-logits · gpt-4o-mini

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     avven
    -0.41
     Cowell
    -0.38
     začet
    -0.37
     Bluestacks
    -0.37
     Cabral
    -0.37
     widerrufen
    -0.36
     mid
    -0.35
    emlrt
    -0.34
     Staff
    -0.34
    ideae
    -0.34
    POSITIVE LOGITS
    SequentialGroup
    0.75
    StoryboardSegue
    0.74
     насељу
    0.68
    eseorang
    0.67
     pinulongan
    0.66
    ArrowToggle
    0.66
    DataAnnotations
    0.66
     AppCompatTheme
    0.65
     NavController
    0.64
    országban
    0.63
    Activations Density 6.069%

    No Known Activations