© 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. 7069
    Prev
    Next
    INDEX
    Explanations

    words and numbers related to technical information and specifications, especially in French.

    oai_token-act-pair · gemini-2.0-flash

    French language

    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
     EconPapers
    -0.68
     مشين
    -0.67
     kasarigan
    -0.64
     mourut
    -0.60
     présidenti
    -0.58
    tagHelperRunner
    -0.55
    Jegyzetek
    -0.54
     découver
    -0.53
     dépens
    -0.52
     militaires
    -0.52
    POSITIVE LOGITS
     ce
    0.58
     cet
    0.51
    بوابة
    0.50
    =$?
    0.49
    kmale
    0.49
    ibatis
    0.49
    igre
    0.49
    Portale
    0.48
     Kreuz
    0.48
     ces
    0.48
    Activations Density 0.947%

    No Known Activations