© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13594
    Prev
    Next
    INDEX
    Explanations

    mentions of data, parameters, significance, and relationships in scientific studies.

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Enllaces
    -0.52
     cena
    -0.46
    ‌آ
    -0.45
    犁
    -0.44
    pull
    -0.43
    NIP
    -0.41
    $_['
    -0.40
    isa
    -0.40
     ap
    -0.40
    ap
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.77
     NSCoder
    0.73
     насељу
    0.73
    IntoConstraints
    0.66
     TextAppearance
    0.64
    🇶
    0.63
     समीक्षक
    0.62
    __(/*!
    0.61
    illoin
    0.60
     ProtoMessage
    0.59
    Activations Density 0.762%

    No Known Activations