© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13090
    Prev
    Next
    INDEX
    Explanations

    javascript code with find and replace functions, especially dealing with file names and paths, as well as single quotes

    oai_token-act-pair · gemini-2.0-flash

    apostrophes and commas

    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
    ########.
    -0.68
     stället
    -0.64
     originaux
    -0.63
     extérieurs
    -0.61
    utilisons
    -0.60
     sécher
    -0.60
    ingway
    -0.59
     الدولى
    -0.59
    RepeatedField
    -0.59
     Vikipedi
    -0.58
    POSITIVE LOGITS
    __(/*!
    0.65
    jsonPath
    0.48
     basic
    0.48
    TagMode
    0.48
    figsize
    0.47
    oide
    0.47
    um
    0.47
     parseFrom
    0.46
    zegor
    0.46
    appendChild
    0.46
    Activations Density 0.256%

    No Known Activations