© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5318
    Prev
    Next
    INDEX
    Explanations

    words related to royalty, territory, and political transitions in Danish and German history

    oai_token-act-pair · gemini-2.0-flash

    Danish royalty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     look
    -1.31
    look
    -1.15
    Look
    -1.12
     Look
    -1.12
     LOOK
    -1.06
     looks
    -0.96
    LOOK
    -0.90
    looks
    -0.84
     looked
    -0.81
     Looks
    -0.78
    POSITIVE LOGITS
    protoimpl
    0.56
     Winaray
    0.54
    PhysRev
    0.53
    MessageOf
    0.53
     تانيه
    0.53
     (!__
    0.51
    []){
    0.49
    riction
    0.49
     betweenstory
    0.49
     eng
    0.48
    Activations Density 0.876%

    No Known Activations