© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11668
    Prev
    Next
    INDEX
    Explanations

    people with terms of age and/or gender

    oai_token-act-pair · gemini-2.0-flash

    elderly and pregnant

    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
    <bos>
    -0.69
     محفوظة
    -0.64
    BeginInit
    -0.57
     Audiodateien
    -0.55
    firmasi
    -0.48
    SBATCH
    -0.47
    出版年
    -0.46
     للمعارف
    -0.45
     hiện
    -0.45
    ANTLR
    -0.45
    POSITIVE LOGITS
    expandindo
    0.54
    IntoConstraints
    0.50
     lexus
    0.50
    ğraf
    0.49
     ſtate
    0.47
    CopyWith
    0.47
     licked
    0.47
     licking
    0.47
    stoy
    0.47
     ftate
    0.45
    Activations Density 0.638%

    No Known Activations