© 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. 1964
    Prev
    Next
    INDEX
    Explanations

    references to scientific papers and data

    oai_token-act-pair · gemini-2.0-flash

    scientific terms related to biological entities

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

    genes biology

    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
     stället
    -0.82
    rungsseite
    -0.78
     saites
    -0.75
    AndEndTag
    -0.74
     fédé
    -0.74
     Signalez
    -0.71
     débats
    -0.71
     fidèles
    -0.69
     enfans
    -0.67
     prêtres
    -0.66
    POSITIVE LOGITS
     molecules
    0.56
    ]--;
    0.54
    déric
    0.51
     genes
    0.51
     properties
    0.51
    WebpackPlugin
    0.50
     proteins
    0.49
     polypep
    0.47
     hormones
    0.47
    vernote
    0.47
    Activations Density 12.447%

    No Known Activations