© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11968
    Prev
    Next
    INDEX
    Explanations

    phrases related to official bureaucratic and legal language

    oai_token-act-pair · gemini-2.0-flash

    Work and personal life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    довать
    -0.54
    CloseOperation
    -0.50
    oplastic
    -0.47
    λασ
    -0.46
    TacToe
    -0.46
    MultipartFile
    -0.45
    довал
    -0.45
    enschappelijke
    -0.44
     Downloads
    -0.43
     octaves
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    достатки
    0.62
    oneph
    0.59
    IVEREF
    0.56
    +```
    0.54
    levis
    0.53
    masing
    0.52
     hjem
    0.52
    AsUp
    0.51
    uminense
    0.51
    Activations Density 0.819%

    No Known Activations