© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7943
    Prev
    Next
    INDEX
    Explanations

    words containing the substring 'step'

    oai_token-act-pair · gemini-2.0-flash

    family relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     disambiguazione
    -0.67
    TagMode
    -0.66
     onCreateView
    -0.59
     ExecuteAsync
    -0.56
    \{\\
    -0.56
    JspWriter
    -0.53
    UrlResolution
    -0.52
    artifactId
    -0.52
     Administrativna
    -0.52
    cticut
    -0.51
    POSITIVE LOGITS
    STEP
    0.54
     Step
    0.53
     step
    0.52
     STEP
    0.51
    Step
    0.50
     tart
    0.50
    ztus
    0.50
    step
    0.50
    存于互联网档案馆
    0.50
     dr
    0.49
    Activations Density 0.745%

    No Known Activations