© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10019
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and syntax.

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    parsedMessage
    -0.90
    AndEndTag
    -0.83
    enumi
    -0.83
    ValueStyle
    -0.80
    +#+#
    -0.80
    RenderAtEndOf
    -0.80
    ьаж
    -0.71
    sizeCache
    -0.71
    MatButtonModule
    -0.70
    webElementXpaths
    -0.68
    POSITIVE LOGITS
              
    0.54
     nedenle
    0.51
    isdir
    0.48
     poils
    0.47
    dataframe
    0.47
    нциклопедия
    0.45
    foy
    0.45
     Foer
    0.45
    umą
    0.44
     kré
    0.44
    Activations Density 0.240%

    No Known Activations