© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5788
    Prev
    Next
    INDEX
    Explanations

    fragmented bits of language like headings, titles, and verbs.

    oai_token-act-pair · gemini-2.0-flash

    Action words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Explore
    -1.09
     Give
    -1.09
     Take
    -1.06
     Tell
    -1.06
     Ask
    -1.05
     Find
    -1.05
     Connect
    -1.05
     Bring
    -1.05
     Get
    -1.05
     Choose
    -1.05
    POSITIVE LOGITS
     ModelExpression
    0.76
     realize
    0.73
     continue
    0.70
     move
    0.69
    fromCharCode
    0.68
     take
    0.68
     do
    0.66
     produce
    0.66
     operate
    0.66
     dàng
    0.66
    Activations Density 3.131%

    No Known Activations