© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13852
    Prev
    Next
    INDEX
    Explanations

    words related to historical significance and preservation

    oai_token-act-pair · gemini-2.0-flash

    historic listings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     betweenstory
    -0.57
    LookAnd
    -0.57
    ThroughAttribute
    -0.55
     asexual
    -0.54
     utafiti
    -0.52
     allá
    -0.51
    ViewFeatures
    -0.51
     Plastic
    -0.51
    Geplaatst
    -0.50
     NUKAT
    -0.50
    POSITIVE LOGITS
     Listed
    0.67
     listed
    0.63
     existing
    0.63
     historic
    0.60
    existing
    0.59
     bestaande
    0.59
    disposing
    0.58
     viewDidLoad
    0.56
    </thead>
    0.56
     listings
    0.54
    Activations Density 2.083%

    No Known Activations