© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15499
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C-like code involving pointers, conditional statements, and memory operations

    oai_token-act-pair · gemini-2.0-flash

    Related to code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -0.79
     PopupWindow
    -0.71
     ContentValues
    -0.68
    ValueStyle
    -0.66
    GraphicsUnit
    -0.66
    djangoproject
    -0.66
     otomatig
    -0.65
    principalColumn
    -0.64
    IntoConstraints
    -0.62
    ViewFeatures
    -0.61
    POSITIVE LOGITS
    надца
    0.38
    lež
    0.36
     DEA
    0.35
    ,&
    0.34
     sirens
    0.34
    ophobic
    0.33
     UPM
    0.33
    semantics
    0.33
     FEC
    0.33
     thác
    0.33
    Activations Density 15.320%

    No Known Activations