© 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. 12933
    Prev
    Next
    INDEX
    Explanations

    quotation marks, commas, numbers, and words related to legal transcripts or numbers referring to amounts of money

    oai_token-act-pair · gemini-2.0-flash

    Formal writing snippets

    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
     điệu
    -0.51
     فا
    -0.46
     Speak
    -0.44
     rolling
    -0.44
     تر
    -0.43
    تر
    -0.43
    rxjs
    -0.43
     Play
    -0.43
     trống
    -0.43
    енча
    -0.43
    POSITIVE LOGITS
    addContainerGap
    0.61
    참고
    0.60
    RenderAtEndOf
    0.59
     iveco
    0.56
     scania
    0.56
    windowFixed
    0.56
    сылкі
    0.55
    UnknownFieldSet
    0.52
    qtype
    0.51
     newOwner
    0.51
    Activations Density 0.132%

    No Known Activations