© 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. 7354
    Prev
    Next
    INDEX
    Explanations

    words and phrases used for business communications, especially in customer service contexts

    oai_token-act-pair · gemini-2.0-flash

    contact-related terms

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

    contact

    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
    ئيس
    -0.47
    hlí
    -0.46
     miliardi
    -0.46
     pronti
    -0.46
     falar
    -0.44
     broadest
    -0.43
     wards
    -0.43
    M
    -0.43
     conversar
    -0.43
     eer
    -0.43
    POSITIVE LOGITS
     me
    1.04
     us
    0.99
     protoimpl
    0.80
     my
    0.74
    RenderAtEndOf
    0.72
    GHIJKLM
    0.70
     propOrder
    0.70
    SuccessListener
    0.68
     myself
    0.68
    myself
    0.67
    Activations Density 2.088%

    No Known Activations