© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11271
    Prev
    Next
    INDEX
    Explanations

    words describing types or categories of things, particularly in formal or technical contexts

    oai_token-act-pair · 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
    PERIOD
    -0.53
    abund
    -0.51
    zuf
    -0.49
    orted
    -0.48
    nelles
    -0.48
    weth
    -0.45
    thur
    -0.45
     periods
    -0.45
     périodes
    -0.43
    rella
    -0.43
    POSITIVE LOGITS
     незавершена
    0.75
     Infórmanos
    0.72
     ujednoznacz
    0.68
     AssemblyVersion
    0.67
    contentLoaded
    0.66
    曖昧さ回避
    0.64
    rungsseite
    0.63
    thâu
    0.62
     Савезне
    0.61
     disambiguazione
    0.61
    Activations Density 5.764%

    No Known Activations