© 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. 10689
    Prev
    Next
    INDEX
    Explanations

    a combination of URLs, the word 'cry', and the word 'eagle'

    oai_token-act-pair · gemini-2.0-flash

    cry

    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
     kasarigan
    -0.79
     Infórmanos
    -0.77
    PhysRev
    -0.77
    protoimpl
    -0.74
    PhysRevD
    -0.71
    PerformLayout
    -0.71
    DeleteBehavior
    -0.71
     Meksiku
    -0.68
     Signalez
    -0.68
     الحره
    -0.66
    POSITIVE LOGITS
     Jaffe
    0.40
     sweetheart
    0.40
     II
    0.40
     et
    0.40
     hạng
    0.40
    nic
    0.38
     III
    0.38
    inemann
    0.38
     await
    0.37
     rendel
    0.37
    Activations Density 0.842%

    No Known Activations