© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14551
    Prev
    Next
    INDEX
    Explanations

    javascript, html, and php code snippets along with code related terms

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    存于互联网档案馆
    -0.69
    hyrchwyd
    -0.68
     $_"
    -0.66
     nahilalakip
    -0.65
     strconv
    -0.65
     Sinon
    -0.65
    drawiam
    -0.65
     كومونز
    -0.64
    Portale
    -0.63
     IBOutlet
    -0.63
    POSITIVE LOGITS
    </h3>
    0.48
    </em>
    0.41
     Id
    0.40
    '}>
    0.40
     мѣ
    0.40
      
    0.40
    ')){
    0.39
    </strong>
    0.39
     we
    0.38
    </h6>
    0.38
    Activations Density 5.807%

    No Known Activations