© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8961
    Prev
    Next
    INDEX
    Explanations

    phone numbers, dates, and other common numerical or business patterns

    oai_token-act-pair · gemini-2.0-flash

    Code/technical reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Six
    -2.03
     six
    -1.88
    6
    -1.79
    Six
    -1.78
    six
    -1.68
     SIX
    -1.66
     sixth
    -1.64
     Sixth
    -1.64
    六
    -1.52
    SIX
    -1.48
    POSITIVE LOGITS
    ThroughAttribute
    0.52
    ArgsConstructor
    0.48
    AccessorTable
    0.46
    mouseup
    0.43
    فایل‌لار
    0.43
     ciz
    0.42
    IsContent
    0.41
    ../../
    0.41
    ען
    0.40
     Pellegrini
    0.40
    Activations Density 15.996%

    No Known Activations