© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12019
    Prev
    Next
    INDEX
    Explanations

    situations involving teaching, proving, or disagreeing

    oai_token-act-pair · gemini-2.0-flash

    academic/legal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     autorytatywna
    -0.84
     propOrder
    -0.82
     мәкал
    -0.81
     resourceCulture
    -0.81
    الحياه
    -0.79
    ConstraintMaker
    -0.79
    
    -0.78
     ویکی‌پدی
    -0.77
    Ligações
    -0.76
     odkazy
    -0.76
    POSITIVE LOGITS
     друг
    0.44
    elum
    0.41
    izas
    0.40
    γχ
    0.40
    äs
    0.40
    zwischen
    0.39
    kur
    0.39
    IFY
    0.39
    toHaveBeenCalled
    0.39
    ại
    0.38
    Activations Density 0.618%

    No Known Activations