© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12791
    Prev
    Next
    INDEX
    Explanations

    code-like fragments, juridical vocabulary, and sleep

    oai_token-act-pair · gemini-2.0-flash

    Code/systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    manteau
    -0.66
     تانيه
    -0.63
    henge
    -0.62
    terness
    -0.59
    iliares
    -0.59
     Fathers
    -0.58
    NTB
    -0.58
    Mothers
    -0.57
    otry
    -0.57
     veil
    -0.57
    POSITIVE LOGITS
    adaptiveStyles
    0.64
    richTextPanel
    0.61
     EconPapers
    0.59
    AddTagHelper
    0.56
     فريبيس
    0.52
     Hutchins
    0.49
    coroutines
    0.47
    QUADS
    0.47
     OFDb
    0.47
     rayons
    0.46
    Activations Density 16.049%

    No Known Activations