© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12427
    Prev
    Next
    INDEX
    Explanations

    words and phrases quantifying amounts and order

    oai_token-act-pair · gemini-2.0-flash

    Math/Technical document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     autorytatywna
    -1.11
     EconPapers
    -0.89
    RenderAtEndOf
    -0.76
     Baru
    -0.74
     يتيمه
    -0.73
    endpush
    -0.73
     дописавши
    -0.71
     GenerationType
    -0.71
    存于互联网档案馆
    -0.67
    AlterField
    -0.65
    POSITIVE LOGITS
    <bos>
    0.63
     drauf
    0.47
     voľ
    0.45
    tencent
    0.44
    toEqual
    0.43
    少なく
    0.42
    umpad
    0.41
    kkue
    0.40
     lahat
    0.40
    ınd
    0.40
    Activations Density 6.008%

    No Known Activations