© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4159
    Prev
    Next
    INDEX
    Explanations

    text in French or references to it.

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act · gemini-2.0-flash

    ▁l

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     térm
    -0.76
     băr
    -0.68
    Erreferentziak
    -0.68
    GEBURTSDATUM
    -0.65
     visuales
    -0.65
     égale
    -0.65
    TypedDataSet
    -0.64
     titolata
    -0.64
     ricev
    -0.63
     artificiales
    -0.63
    POSITIVE LOGITS
    CRETE
    0.58
    🏼
    0.57
     betweenstory
    0.56
     cas
    0.54
    ADVERTISEMENT
    0.52
    phorbia
    0.51
    meester
    0.50
     bezeichneter
    0.50
    🏽
    0.49
     
    0.49
    Activations Density 0.309%

    No Known Activations