© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15069
    Prev
    Next
    INDEX
    Explanations

    Spanish words related to programming or logic

    oai_token-act-pair · gemini-2.0-flash

    Spanish language context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     NSCoder
    -1.10
    onViewCreated
    -1.00
     ujednoznacz
    -0.86
    djangoproject
    -0.86
    Numerology
    -0.85
    oredCriteria
    -0.84
    parsedMessage
    -0.83
    :+:
    -0.83
    UserScript
    -0.83
    ########.
    -0.82
    POSITIVE LOGITS
    ıştı
    0.41
     ter
    0.37
    hai
    0.36
    wiec
    0.36
    ząt
    0.35
     }}"></
    0.35
    mis
    0.34
     тик
    0.34
     spra
    0.34
    aux
    0.33
    Activations Density 0.743%

    No Known Activations