© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5219
    Prev
    Next
    INDEX
    Explanations

    uses of "they" near the word 'so', and related to laws, rules, and confusion

    oai_token-act-pair · gemini-2.0-flash

    software development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     noires
    -0.58
     spirituale
    -0.53
     russes
    -0.50
     popolo
    -0.49
     aiment
    -0.49
     citoy
    -0.49
     fédé
    -0.48
     africains
    -0.48
     debout
    -0.48
     skj
    -0.47
    POSITIVE LOGITS
     GenerationType
    0.77
    ScopeManager
    0.70
    mybatisplus
    0.69
    makeText
    0.63
    delwed
    0.62
    lapsingToolbar
    0.61
    EnableWeb
    0.61
    DOCTYPE
    0.60
     EdgeInsets
    0.59
    ValueStyle
    0.58
    Activations Density 1.415%

    No Known Activations