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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11151
    Prev
    Next
    INDEX
    Explanations

    the word "should" or words associated with feeling obligated

    oai_token-act-pair · gemini-2.0-flash

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     should
    -1.95
    should
    -1.77
    Should
    -1.75
     Should
    -1.63
     fhould
    -1.41
     SHOULD
    -1.33
     sollte
    -1.28
     sollten
    -1.28
     devraient
    -1.20
    hould
    -1.20
    POSITIVE LOGITS
    SerializeField
    0.56
     تضيفلها
    0.53
     fair
    0.50
    الإنجليزية
    0.50
     Fair
    0.47
    ports
    0.46
    nonatomic
    0.46
    érons
    0.46
    wra
    0.45
     wel
    0.45
    Activations Density 0.415%

    No Known Activations