© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 994
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to postal services

    oai_token-act-pair · gemini-2.0-flash

    post office

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    hires
    -0.51
     interesar
    -0.50
     froide
    -0.48
     sauvages
    -0.48
     achet
    -0.47
    spender
    -0.47
     présentés
    -0.46
     prêts
    -0.46
     vš
    -0.46
     nettoyer
    -0.45
    POSITIVE LOGITS
    <bos>
    0.89
     postal
    0.79
     postage
    0.77
     USPS
    0.73
     mail
    0.71
     postman
    0.70
     насељу
    0.70
     delivery
    0.70
     nahilalakip
    0.68
     Postal
    0.68
    Activations Density 0.326%

    No Known Activations