© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11109
    Prev
    Next
    INDEX
    Explanations

    mentions of soccer player John, his actions, and the names of teams

    oai_token-act-pair · gemini-2.0-flash

    Sports signings and contracts

    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
    +#+#
    -0.82
     Reverso
    -0.71
    AutoresizingMask
    -0.69
    جغرافيا
    -0.68
     ElementRef
    -0.66
    تفصیلات
    -0.65
    sizeCache
    -0.64
    Források
    -0.64
     jspb
    -0.63
     Audiodateien
    -0.62
    POSITIVE LOGITS
     getan
    0.44
    ']))
    0.41
     extended
    0.39
     oyna
    0.38
     loan
    0.38
    #+#
    0.38
     tå
    0.36
    XmlEnum
    0.36
     pozn
    0.36
    復
    0.35
    Activations Density 0.437%

    No Known Activations