© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13375
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to negative or positive attributes of people

    oai_token-act-pair · gemini-2.0-flash

    People's roles and descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ProgressHUD
    -0.52
     ujednoznacz
    -0.46
    WithIOException
    -0.45
    tvguidetime
    -0.43
     ["",
    -0.43
    goku
    -0.42
    inkling
    -0.42
     nourrir
    -0.41
     alimentare
    -0.41
    نق
    -0.40
    POSITIVE LOGITS
     performer
    0.75
    comers
    0.73
     performers
    0.71
    comer
    0.70
     starter
    0.70
     Cæsar
    0.70
     setters
    0.67
     solver
    0.66
    GraphicsUnit
    0.66
     IBRARY
    0.66
    Activations Density 0.728%

    No Known Activations