© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5979
    Prev
    Next
    INDEX
    Explanations

    phrases with the passive voice that indicate research results

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     created
    -0.83
     formed
    -0.73
    formed
    -0.69
     generated
    -0.69
     achieved
    -0.68
     established
    -0.68
     introduced
    -0.67
     produced
    -0.67
     issued
    -0.66
    posted
    -0.66
    POSITIVE LOGITS
     dowry
    0.57
    NewUrlParser
    0.56
    AutoScaleMode
    0.52
     abenço
    0.49
    Filmografie
    0.48
     Eup
    0.47
     giras
    0.47
     indipendente
    0.47
     cristianismo
    0.47
     policiales
    0.45
    Activations Density 3.638%

    No Known Activations