© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9866
    Prev
    Next
    INDEX
    Explanations

    French words and words used in French conversation.

    oai_token-act-pair · gemini-2.0-flash

    French prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     the
    -1.03
    )];
    -0.69
     this
    -0.65
    ########.
    -0.60
     these
    -0.60
     its
    -0.59
     his
    -0.59
     mergeFrom
    -0.59
    />,
    -0.59
     EconPapers
    -0.58
    POSITIVE LOGITS
     prochaines
    0.66
     âmes
    0.66
     têtes
    0.64
     lèvres
    0.63
     larmes
    0.62
     preuves
    0.61
     ladite
    0.60
     nourrir
    0.60
     cœurs
    0.59
     tacón
    0.59
    Activations Density 2.017%

    No Known Activations