© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7461
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abstract and introduction of scientific papers about evolution or genetics

    oai_token-act-pair · gemini-2.0-flash

    reptiles, specifically lizards

    np_token-act-pair-logits · gpt-4o-mini

    Reptiles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     nonUne
    -0.71
     ujednoznacz
    -0.67
    oredCriteria
    -0.66
     UIAlert
    -0.63
    Referanser
    -0.63
    EndInit
    -0.61
     препратки
    -0.60
    
    -0.59
    зулта
    -0.59
     cherchés
    -0.58
    POSITIVE LOGITS
     scales
    0.61
     rep
    0.58
    Rep
    0.56
     Rep
    0.54
    rep
    0.53
     scaled
    0.52
     lizard
    0.51
    scales
    0.50
     snake
    0.49
     crocodile
    0.48
    Activations Density 1.526%

    No Known Activations