© 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. 12661
    Prev
    Next
    INDEX
    Explanations

    single character variables often used as counters or temporary math variables

    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_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
    ImageContext
    -0.81
     lenker
    -0.76
    "):
    -0.65
     Administrativna
    -0.65
    참고
    -0.65
    ".
    -0.65
    ----</
    -0.64
    ：
    -0.62
    IKit
    -0.60
    zburg
    -0.60
    POSITIVE LOGITS
    جل
    0.39
    expense
    0.37
    labelledby
    0.36
    ünsche
    0.36
     Philosophical
    0.35
    ReadLine
    0.35
    chaik
    0.34
    oppo
    0.34
    LITERAL
    0.33
    SEVERE
    0.33
    Activations Density 1.046%

    No Known Activations