© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13133
    Prev
    Next
    INDEX
    Explanations

    words reflecting importance and common every day occurances.

    oai_token-act-pair · gemini-2.0-flash

    say "t" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Italijanski
    -0.68
     để
    -0.65
     чтобы
    -0.65
     щоб
    -0.64
     untuk
    -0.61
     να
    -0.60
    rawDesc
    -0.60
    To
    -0.59
    TypedDataSet
    -0.57
     pinulongan
    -0.57
    POSITIVE LOGITS
     t
    0.90
     ta
    0.85
     top
    0.81
     ton
    0.71
     tu
    0.70
     TOP
    0.66
     Top
    0.63
     td
    0.60
    top
    0.60
     ti
    0.59
    Activations Density 2.014%

    No Known Activations