© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2908
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to treating others with respect

    oai_token-act-pair · gemini-2.0-flash

    respectful behavior

    np_token-act-pair-logits · gpt-4o-mini

    Respect and kindness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     financières
    -0.49
     utility
    -0.44
    WithIOException
    -0.44
     nocturna
    -0.43
    baomidou
    -0.43
     rêver
    -0.42
     sayap
    -0.40
     noires
    -0.40
     fondament
    -0.40
     Stretcher
    -0.40
    POSITIVE LOGITS
    ThroughAttribute
    0.79
    Tembelea
    0.76
    kháu
    0.76
     defaultstate
    0.75
     courteous
    0.74
     kindly
    0.72
     оригіналу
    0.71
     polite
    0.69
    хьтан
    0.66
     '{@
    0.65
    Activations Density 1.236%

    No Known Activations