© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6689
    Prev
    Next
    INDEX
    Explanations

    scientific writing about chemical compounds, particularly oil-water mixtures

    oai_token-act-pair · gemini-2.0-flash

    terms related to foam

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

    foam

    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
     Administrativna
    -0.90
    tagHelperRunner
    -0.83
     nahilalakip
    -0.78
     lenker
    -0.77
    rrggbb
    -0.69
    DrawerToggle
    -0.63
    sanity
    -0.60
    UnusedPrivate
    -0.59
    RegressionTest
    -0.56
     Theſe
    -0.56
    POSITIVE LOGITS
     foam
    0.97
     espuma
    0.90
     fro
    0.85
     fo
    0.84
    Foam
    0.82
    foam
    0.82
     Foam
    0.79
     l
    0.79
     su
    0.76
    fo
    0.73
    Activations Density 1.736%

    No Known Activations