© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    references to tests performed on animals or children

    oai_token-act-pair · gemini-2.0-flash

    rats

    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
     uska
    -0.54
    ntesis
    -0.45
    atguigu
    -0.44
    erover
    -0.44
    raw
    -0.43
     opération
    -0.42
     protocol
    -0.42
    PrototypeOf
    -0.42
     кра
    -0.42
    <bos>
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.62
    UserScript
    0.61
     NSCoder
    0.61
     BoxDecoration
    0.60
    inafter
    0.58
     sanitaires
    0.57
    ArgsConstructor
    0.57
    󠁢
    0.57
    onViewCreated
    0.56
    BooleanField
    0.56
    Activations Density 0.775%

    No Known Activations