© 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. 7191
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people who are being described

    oai_token-act-pair · gemini-2.0-flash

    verbs related to identity or existence

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

    who

    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
    mybatisplus
    -0.73
     Zijn
    -0.63
    NUMX
    -0.62
    ynos
    -0.60
     للمعارف
    -0.60
    
    -0.59
     Aren
    -0.58
    حياته
    -0.58
     NSCoder
    -0.58
    complexContent
    -0.57
    POSITIVE LOGITS
     is
    0.91
     was
    0.85
     has
    0.80
     venait
    0.65
     resides
    0.63
     serves
    0.60
     had
    0.59
    has
    0.57
     lacks
    0.57
     owes
    0.56
    Activations Density 2.127%

    No Known Activations