© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 56
    Prev
    Next
    INDEX
    Explanations

    dates, scores, and team names in a sports context

    oai_token-act-pair · gemini-2.0-flash

    sports scores and standings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     kasarigan
    -0.92
     estekak
    -0.61
     ویکی‌پدی
    -0.60
    +#+#
    -0.59
    LookAnd
    -0.58
    ьаж
    -0.57
     externi
    -0.57
    IntoConstraints
    -0.57
    ]")]
    -0.57
    Palmar
    -0.55
    POSITIVE LOGITS
    ⓘ
    0.74
    ulator
    0.50
     correctes
    0.50
     such
    0.49
     mpl
    0.48
    œuf
    0.47
    LayoutStyle
    0.47
     télévisée
    0.47
     multer
    0.47
    ctor
    0.47
    Activations Density 2.111%

    No Known Activations