© 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. 11120
    Prev
    Next
    INDEX
    Explanations

    the word "recent" and words that appear alongisde it

    oai_token-act-pair · gemini-2.0-flash

    recent

    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
    awtextra
    -0.84
     autorytatywna
    -0.81
    WebElementEntity
    -0.79
     disambiguazione
    -0.79
    #+#
    -0.77
     noDo
    -0.75
     Huguen
    -0.74
    DFT
    -0.72
    Sqft
    -0.71
    ViewFeatures
    -0.69
    POSITIVE LOGITS
     giro
    0.54
     finalised
    0.54
     apologise
    0.54
    COMPLETE
    0.52
     utilising
    0.52
     utilise
    0.51
     newest
    0.50
    0.50
     P
    0.49
     privatisation
    0.49
    Activations Density 0.243%
    No Known Activations