© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12639
    Prev
    Next
    INDEX
    Explanations

    proper nouns, often related to organizations, combined with words suggesting regulations, names or contact information.

    oai_token-act-pair · gemini-2.0-flash

    organizations and web addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     noqa
    -0.50
    quisition
    -0.48
     credere
    -0.46
     sute
    -0.46
     industry
    -0.44
     business
    -0.44
    }{*}{
    -0.44
     الشركة
    -0.43
     Компа
    -0.43
    letoe
    -0.42
    POSITIVE LOGITS
     <=",
    0.82
    AndEndTag
    0.73
     ddelweddau
    0.73
    anmoins
    0.69
    onAttach
    0.67
    UNRELATED
    0.67
    ArgsConstructor
    0.64
     kasarigan
    0.63
    oczes
    0.61
    forChild
    0.61
    Activations Density 7.449%

    No Known Activations