© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11301
    Prev
    Next
    INDEX
    Explanations

    French words, especially those related to organizations or institutions

    oai_token-act-pair · gemini-2.0-flash

    French

    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_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
     fermés
    -0.77
     mauvaises
    -0.64
     seuls
    -0.63
    
    -0.63
     oeufs
    -0.63
    -------------</
    -0.63
    verwijspagina
    -0.61
     rempliss
    -0.60
     boissons
    -0.60
     noires
    -0.59
    POSITIVE LOGITS
    ^(@)
    0.52
     Colomb
    0.44
    ^(@
    0.43
     purpoſe
    0.42
    itario
    0.42
     Courant
    0.42
    saurus
    0.41
    voerd
    0.40
     Philist
    0.40
    roscope
    0.40
    Activations Density 0.723%

    No Known Activations