© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12587
    Prev
    Next
    INDEX
    Explanations

    words referring to a time or place where something occurs or exists

    oai_token-act-pair · gemini-2.0-flash

    location, existence, or time

    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
    ec
    -0.49
     createContext
    -0.45
    στό
    -0.45
    ela
    -0.45
    mità
    -0.43
     lov
    -0.43
    bed
    -0.43
     aggiunto
    -0.42
    porte
    -0.42
    RunAsync
    -0.42
    POSITIVE LOGITS
     gynhyrchwyd
    0.90
    RenderAtEndOf
    0.86
     autorytatywna
    0.82
     MainAxisSize
    0.73
    ագրություններ
    0.68
    IntoConstraints
    0.65
     CreateTagHelper
    0.64
     kasarigan
    0.64
     esq
    0.62
     ChromeDriver
    0.61
    Activations Density 2.314%

    No Known Activations