© 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. 4888
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by "be"

    oai_token-act-pair · gemini-2.0-flash

    formal writing

    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
     acoper
    -0.53
     correctes
    -0.47
    msc
    -0.46
    #.
    -0.46
     failure
    -0.45
    şekkür
    -0.44
     gând
    -0.43
    覆盖
    -0.43
    ]--;
    -0.43
    UNDEFINED
    -0.42
    POSITIVE LOGITS
    :✨
    0.69
    BagLayout
    0.60
    onAttach
    0.59
    createCanvas
    0.59
    曖昧さ回避
    0.59
    migrationBuilder
    0.59
     Paglinawan
    0.59
     saites
    0.57
    marshaller
    0.57
    Bakgrunnsstoff
    0.56
    Activations Density 1.761%

    No Known Activations