© 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. 14621
    Prev
    Next
    INDEX
    Explanations

    LaTeX math delimiters or code

    oai_token-act-pair · gemini-2.0-flash

    j

    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
    <bos>
    -1.00
     akong
    -0.45
    تیب
    -0.45
    unnitel
    -0.45
     itſelf
    -0.44
     مواليد
    -0.43
     sconfit
    -0.41
    Plan
    -0.40
    ัติ
    -0.40
     myſelf
    -0.40
    POSITIVE LOGITS
     JAXBElement
    0.70
    parsedMessage
    0.68
    ghold
    0.66
     jScrollPane
    0.64
    +#+#
    0.64
    htbp
    0.61
    elemField
    0.60
     Theore
    0.59
     Aware
    0.59
    ofo
    0.59
    Activations Density 15.480%

    No Known Activations