© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14287
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal consents, offers, app purchases, and agreements

    oai_token-act-pair · gemini-2.0-flash

    agreement/compliance

    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
    GEBURTSDATUM
    -0.71
    HasAnnotation
    -0.67
     '\\;'
    -0.60
    NameInMap
    -0.57
    openzeppelin
    -0.56
     getItemId
    -0.54
    ">//
    -0.54
     intptr
    -0.54
    errHandler
    -0.53
    iffany
    -0.52
    POSITIVE LOGITS
    Transcripción
    0.54
    jalá
    0.54
     débit
    0.52
     lèvres
    0.51
     aéreas
    0.51
     télécommande
    0.51
     intercal
    0.49
     beden
    0.49
    InSection
    0.49
     calves
    0.49
    Activations Density 2.544%

    No Known Activations