© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6367
    Prev
    Next
    INDEX
    Explanations

    words or short phrases with emphasis through unusual spelling and capitalization

    oai_token-act-pair · gemini-2.0-flash

    nonsensical text

    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
     typelib
    -0.77
    AntiForgeryToken
    -0.77
    BagLayout
    -0.71
    LayoutStyle
    -0.67
     itſelf
    -0.65
    ücks
    -0.64
    UnknownFieldSet
    -0.63
    InputBorder
    -0.62
     postIndex
    -0.61
    modb
    -0.60
    POSITIVE LOGITS
    ood
    0.49
    ped
    0.48
    过
    0.47
     过
    0.42
     Likewise
    0.41
     ra
    0.41
    ğinde
    0.40
    過
    0.38
     Vergangenheit
    0.38
    Likewise
    0.38
    Activations Density 1.051%

    No Known Activations