© 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. 7178
    Prev
    Next
    INDEX
    Explanations

    the last name "Han"

    oai_token-act-pair · gemini-2.0-flash

    tokens containing the substring 'Han'

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

    Han

    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
     intptr
    -0.72
    例句
    -0.55
    VIAF
    -0.54
    Vorlage
    -0.52
     judiciaire
    -0.50
     Saks
    -0.45
    andt
    -0.43
    bcryptjs
    -0.43
     ISNI
    -0.43
     Jump
    -0.43
    POSITIVE LOGITS
    Autoritní
    0.81
     فريبيس
    0.72
     Савезне
    0.68
     myſelf
    0.58
     gynhyrchwyd
    0.57
     uſe
    0.57
    thée
    0.57
    omeness
    0.57
     greateſt
    0.57
     uſed
    0.56
    Activations Density 0.222%

    No Known Activations