© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3322
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     cesse
    -0.64
     faltan
    -0.58
     taglia
    -0.56
     have
    -0.55
     tramonto
    -0.52
     nôtre
    -0.52
     épaules
    -0.52
     planète
    -0.51
     nécessité
    -0.51
    astify
    -0.50
    POSITIVE LOGITS
    <bos>
    0.65
     propOrder
    0.63
     indisponible
    0.60
    featureID
    0.56
    bigsqcup
    0.56
    polated
    0.55
     expansion
    0.55
    ########.
    0.54
     pleaſure
    0.54
    };*/
    0.54
    Activations Density 1.944%

    No Known Activations