© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11625
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that are commonly used and have a particular semantic meaning across various contexts

    oai_token-act-pair · 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
     defaultstate
    -0.73
    __':
    
    -0.68
    CppCodeGen
    -0.65
    %");
    -0.65
    %")
    -0.63
    $}}
    -0.63
    ()))
    
    -0.62
    __:
    -0.61
     tartalomajánló
    -0.61
     }}$}
    -0.61
    POSITIVE LOGITS
     but
    0.53
    APOLIS
    0.49
    but
    0.48
     colspan
    0.47
    omitempty
    0.47
    But
    0.45
    anskje
    0.43
    šlo
    0.43
    inc
    0.42
    min
    0.42
    Activations Density 3.537%

    No Known Activations