© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13082
    Prev
    Next
    INDEX
    Explanations

    uses of the word "require" in code

    oai_token-act-pair · gemini-2.0-flash

    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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     nakalista
    -0.73
    ]='\
    -0.69
    oubted
    -0.68
     Plan
    -0.66
    nonatomic
    -0.66
    sitions
    -0.66
     nonatomic
    -0.66
    openzeppelin
    -0.65
     addSubview
    -0.65
    Erreferentziak
    -0.64
    POSITIVE LOGITS
     voici
    0.47
     tantum
    0.45
    op
    0.43
    ho
    0.40
     urma
    0.39
     religieuses
    0.39
    back
    0.38
     imig
    0.38
    us
    0.38
    ka
    0.38
    Activations Density 9.569%

    No Known Activations