© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2493
    Prev
    Next
    INDEX
    Explanations

    common words such as articles and prepositions found within a paragraph

    oai_token-act-pair · gemini-2.0-flash

    French and English text

    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
    expandindo
    -0.91
     />";
    -0.78
    RenderAtEndOf
    -0.71
    HostException
    -0.59
    posedge
    -0.57
     useRouter
    -0.57
     frock
    -0.56
    ConstraintMaker
    -0.56
    IsContent
    -0.56
    =*/
    -0.56
    POSITIVE LOGITS
    <bos>
    0.61
    CodeAttribute
    0.55
    featureID
    0.52
    ⓧ
    0.49
    Дереккөздер
    0.48
    indeki
    0.47
    mær
    0.46
    kémon
    0.46
    celona
    0.46
     Ause
    0.46
    Activations Density 3.420%

    No Known Activations