© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3330
    Prev
    Next
    INDEX
    Explanations

    language about financial support or sponsorship for an organization

    oai_token-act-pair · gemini-2.0-flash

    funding and support

    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
    SequentialGroup
    -1.00
     CreateTagHelper
    -0.85
     незавершена
    -0.85
     viewType
    -0.81
     propOrder
    -0.80
    yntaxException
    -0.79
    ReusableCell
    -0.79
    featureID
    -0.77
    setVerticalGroup
    -0.76
    matchCondition
    -0.73
    POSITIVE LOGITS
    <bos>
    1.35
    '
    0.48
     contributo
    0.47
    PageIndex
    0.46
    ]<<"
    0.45
    dorfer
    0.43
    writel
    0.43
    つけて
    0.43
    ⓘ
    0.43
    onSelect
    0.42
    Activations Density 2.071%

    No Known Activations