© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13957
    Prev
    Next
    INDEX
    Explanations

    various syntax elements of programming languages, such as delimiters, keywords, and operators

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ↵↵
    -0.52
    succ
    -0.47
     for
    -0.45
     actual
    -0.43
     su
    -0.41
    (())
    -0.41
     poor
    -0.41
     succ
    -0.40
     executive
    -0.40
     to
    -0.40
    POSITIVE LOGITS
     للمعارف
    0.92
    الدراسه
    0.81
     createSlice
    0.80
     initComponents
    0.79
     Majefty
    0.77
     Efq
    0.77
     NSCoder
    0.75
    الحياه
    0.73
    verwijspagina
    0.73
     Baillargeon
    0.73
    Activations Density 1.832%

    No Known Activations