© 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. 6247
    Prev
    Next
    INDEX
    Explanations

    uses of the word "be" regardless of tense or context

    oai_token-act-pair · gemini-2.0-flash

    repair/maintenance

    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
     corrientes
    -0.45
    LayoutStyle
    -0.44
     atteinte
    -0.43
     vált
    -0.43
     Dod
    -0.40
    모
    -0.40
    hills
    -0.40
    un
    -0.40
     compréhen
    -0.39
    PLING
    -0.39
    POSITIVE LOGITS
     Audiodateien
    0.92
     betweenstory
    0.82
    createCanvas
    0.82
     تضيفلها
    0.75
    TagHelper
    0.73
    出版年
    0.71
    ंदीखरीदारी
    0.69
     &___
    0.69
     يتيمه
    0.68
    NameInMap
    0.68
    Activations Density 0.782%

    No Known Activations