© 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. 13648
    Prev
    Next
    INDEX
    Explanations

    strings describing events or changes in time

    oai_token-act-pair · gemini-2.0-flash

    words related to building actions or statuses

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

    was

    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
    endphp
    -0.64
    kuuta
    -0.62
     estekak
    -0.60
    Parcelize
    -0.59
     bisous
    -0.58
    mycompany
    -0.56
    PRNewswire
    -0.56
    NameInMap
    -0.56
    gående
    -0.55
     ích
    -0.55
    POSITIVE LOGITS
     open
    0.50
     amet
    0.48
     opened
    0.47
     staffed
    0.47
    Читати
    0.46
     Sử
    0.46
     Serif
    0.46
     usages
    0.45
     ens
    0.45
     rans
    0.44
    Activations Density 1.464%

    No Known Activations