Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 983
    Prev
    Next
    INDEX
    Explanations

    variations of the phrase "get [something] to"

    oai_token-act-pair · gemini-2.0-flash

    get...to

    np_token-act-pair-logits · gemini-2.0-flash

    Obtaining or achieving something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
     Offisielt
    -0.48
    enlace
    -0.47
     Cradle
    -0.46
     memerlukan
    -0.42
    شوف
    -0.41
     Mili
    -0.41
     setia
    -0.41
    遠
    -0.41
     Summit
    -0.41
     buttons
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.97
    ReusableCell
    0.72
    endpush
    0.67
    extAlignment
    0.62
    DockStyle
    0.59
    awtextra
    0.58
     estekak
    0.58
    tagext
    0.57
    ConstraintMaker
    0.55
    }))
    
    0.54
    Activations Density 0.937%

    No Known Activations