© 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. 12023
    Prev
    Next
    INDEX
    Explanations

    added lines in code, and the word "each, "bail", and code related operations

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    TypedDataSet
    -0.56
     amnesia
    -0.47
    XMLSchema
    -0.47
    ďte
    -0.45
     Theil
    -0.44
    SequentialGroup
    -0.44
     namin
    -0.43
    Попис
    -0.43
     vayas
    -0.42
    fromCharCode
    -0.42
    POSITIVE LOGITS
    rawDesc
    0.69
    Autoritní
    0.60
    ipers
    0.59
    
    0.58
     autorytatywna
    0.58
    rungsseite
    0.54
    ofold
    0.53
    aites
    0.53
     StatelessWidget
    0.53
    Дереккөздер
    0.52
    Activations Density 0.042%

    No Known Activations