© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15105
    Prev
    Next
    INDEX
    Explanations

    angle brackets, curly braces, parentheses, semicolons, and other characters used in programming languages

    oai_token-act-pair · gemini-2.0-flash

    code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Efq
    -0.84
     AssemblyProduct
    -0.82
    ")));
    -0.76
     particulières
    -0.73
    ")
    -0.71
     Jefus
    -0.69
    ".
    -0.68
    .")
    -0.67
     itſelf
    -0.67
    ")){
    -0.65
    POSITIVE LOGITS
    TagMode
    0.48
    DockStyle
    0.47
     }.
    0.47
     Foy
    0.45
    awtextra
    0.43
    lhes
    0.43
     **)
    0.43
     *__
    0.42
    kháu
    0.42
    fromCharCode
    0.41
    Activations Density 2.472%

    No Known Activations