© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7022
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in the context of retail stores and customer service

    oai_token-act-pair · gemini-2.0-flash

    terms related to retail and checkout areas

    np_token-act-pair-logits · gpt-4o-mini

    Counter/register

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    FormTagHelper
    -0.95
    SequentialGroup
    -0.86
    Brainz
    -0.81
     Paglinawan
    -0.80
     resourceCulture
    -0.79
    Datuak
    -0.79
     الحره
    -0.77
    URLException
    -0.76
     imageNamed
    -0.71
    पया
    -0.71
    POSITIVE LOGITS
     counter
    1.22
    counter
    1.05
     Counter
    0.98
    Counter
    0.95
    COUNTER
    0.89
     register
    0.89
     counters
    0.85
     COUNTER
    0.84
     display
    0.74
    counters
    0.71
    Activations Density 1.279%

    No Known Activations