© 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. 9190
    Prev
    Next
    INDEX
    Explanations

    text related to a specific Indian festival, place, or cultural event involving lights and records.

    oai_token-act-pair · gemini-2.0-flash

    Short words from mixed topics

    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
    Ĝ
    -0.48
    endphp
    -0.47
    Hozzáférés
    -0.46
    ])));
    -0.44
     accett
    -0.44
    istungen
    -0.43
    )}_{
    -0.43
    arXiv
    -0.43
    pulo
    -0.42
    └──
    -0.41
    POSITIVE LOGITS
     FetchType
    0.71
    Datuak
    0.69
     propOrder
    0.65
    Личная
    0.62
    UnknownFieldSet
    0.59
     виправивши
    0.57
    IsContent
    0.56
    Geplaatst
    0.54
     Deacon
    0.54
    下载附件
    0.54
    Activations Density 3.377%

    No Known Activations