© 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. 13777
    Prev
    Next
    INDEX
    Explanations

    words related to partnerships, sponsorships, tours and national events

    oai_token-act-pair · gemini-2.0-flash

    words related to support or partnership

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

    company announcements

    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
    afficheront
    -0.66
    ^(@)
    -0.58
     doInBackground
    -0.54
     ComVisible
    -0.52
    ẢN
    -0.51
     NSCoder
    -0.49
    Gambas
    -0.48
     noexcept
    -0.48
     Hammers
    -0.48
     afield
    -0.48
    POSITIVE LOGITS
     Presenting
    0.52
    Presenting
    0.47
    //
    0.47
    racene
    0.47
    TypedDataSet
    0.46
    feldt
    0.45
    reed
    0.45
    zner
    0.45
     print
    0.45
     lead
    0.45
    Activations Density 1.678%

    No Known Activations