© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13479
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the duties and titles of people working in government or official institutions

    oai_token-act-pair · gemini-2.0-flash

    News/Biographical descriptions

    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
     freilich
    -0.65
     ohnehin
    -0.63
     förm
    -0.61
     guère
    -0.60
    けっこう
    -0.60
     econômica
    -0.57
     nonetheless
    -0.56
    何况
    -0.56
     }{
    -0.56
    うれ
    -0.55
    POSITIVE LOGITS
    
    0.78
    Whilst
    0.75
    ########.
    0.73
    #+#
    0.71
     Whilst
    0.71
     utilising
    0.71
     localisation
    0.68
    itisation
    0.68
     Utili
    0.67
     whilst
    0.67
    Activations Density 7.266%

    No Known Activations