© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5407
    Prev
    Next
    INDEX
    Explanations

    text with French characters and common French words

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     houſe
    -1.19
     Houſe
    -1.13
     purpoſe
    -1.10
     itſelf
    -1.06
     fubject
    -1.05
     myſelf
    -1.04
     themſelves
    -1.04
     becauſe
    -1.03
     himſelf
    -1.03
     ſta
    -1.02
    POSITIVE LOGITS
     et
    0.38
    ouest
    0.36
    Bonsoir
    0.28
    仏
    0.28
     en
    0.28
     berkata
    0.28
    ImmutableList
    0.27
     llantas
    0.26
     qui
    0.25
     n
    0.25
    Activations Density 3.457%

    No Known Activations