© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14603
    Prev
    Next
    INDEX
    Explanations

    words or short phrases in languages other than English, especially Spanish, Croatian, and French, as well as some programming keywords and abbreviations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AndEndTag
    -1.01
    ArgsConstructor
    -0.93
    GEBURTSDATUM
    -0.90
    لينكات
    -0.85
    UnknownFields
    -0.85
     المعيارى
    -0.84
    UnusedPrivate
    -0.81
    Manbalar
    -0.79
     مشين
    -0.78
    SourceChecksum
    -0.77
    POSITIVE LOGITS
     suivants
    0.41
     recientemente
    0.41
    kwds
    0.40
     recentes
    0.39
    inn
    0.37
     käs
    0.37
     catégories
    0.36
     appena
    0.35
     nejs
    0.35
     léka
    0.35
    Activations Density 12.864%

    No Known Activations