© 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. 15253
    Prev
    Next
    INDEX
    Explanations

    french reflexive pronouns

    oai_token-act-pair · gemini-2.0-flash

    French chat logs

    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
     سكانية
    -0.78
     pinulongan
    -0.78
    verwijspagina
    -0.64
    #+#
    -0.63
     estimés
    -0.62
    oredCriteria
    -0.59
    ьаж
    -0.59
    MigrationBuilder
    -0.59
     חיצוניים
    -0.58
    ंदीखरीदारी
    -0.58
    POSITIVE LOGITS
    jstor
    0.54
    WSGI
    0.52
     Stabilization
    0.52
    arrête
    0.49
     trouvait
    0.48
     endblock
    0.47
    explique
    0.47
    rush
    0.46
     muualla
    0.46
    tellt
    0.45
    Activations Density 0.276%

    No Known Activations