© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4902
    Prev
    Next
    INDEX
    Explanations

    a set of words often found in user reviews related to sales, commerce and shopping

    oai_token-act-pair · gemini-2.0-flash

    stock

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ########.
    -0.57
    waterfall
    -0.56
     endwhile
    -0.51
    gbaar
    -0.49
     sienta
    -0.49
    Stayed
    -0.48
     ligaments
    -0.47
    omyia
    -0.47
     getRequest
    -0.45
    графії
    -0.45
    POSITIVE LOGITS
     stock
    3.08
    stock
    2.59
     Stock
    2.56
    Stock
    2.53
     STOCK
    2.48
     stocks
    2.44
    STOCK
    2.36
    stocks
    2.16
     Stocks
    2.02
    Stocks
    1.94
    Activations Density 2.056%

    No Known Activations