© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11940
    Prev
    Next
    INDEX
    Explanations

    words on the topic of babies and diapers

    oai_token-act-pair · gemini-2.0-flash

    Family abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ujednoznacz
    -0.75
    Personensuche
    -0.65
    queryInterface
    -0.64
     '\\;'
    -0.63
    featureID
    -0.60
    الإنجليزية
    -0.59
    rungsseite
    -0.58
     UIAlert
    -0.57
     snippetHide
    -0.57
    ParallelGroup
    -0.57
    POSITIVE LOGITS
     DH
    0.99
     DS
    0.99
     DD
    0.98
     dh
    0.84
     dd
    0.81
    DH
    0.77
     Ds
    0.76
     Dh
    0.71
    DS
    0.69
     ds
    0.68
    Activations Density 1.940%

    No Known Activations