© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11212
    Prev
    Next
    INDEX
    Explanations

    sentences describing someone's work history, using time-related and connective words and sometimes indicating current or past conditions.

    oai_token-act-pair · gemini-2.0-flash

    describing people's experiences

    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
    tierrez
    -0.56
    HomeAsUpEnabled
    -0.55
    awtextra
    -0.54
    ObjectContext
    -0.53
    IsPostBack
    -0.50
    inburgh
    -0.49
    Obrázky
    -0.45
    estacks
    -0.44
    chum
    -0.44
    MLLoader
    -0.43
    POSITIVE LOGITS
    openqa
    0.62
    CloseOperation
    0.61
     co
    0.61
    TemporalType
    0.57
     impressed
    0.57
     flattered
    0.56
     employed
    0.56
     newInstance
    0.55
    WithMany
    0.54
    tious
    0.54
    Activations Density 0.599%

    No Known Activations