© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6828
    Prev
    Next
    INDEX
    Explanations

    strings representing names with initials and suffixes and their locations.

    oai_token-act-pair · gemini-2.0-flash

    variations of the name "Yu"

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

    Yu, Ye, Ya

    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
    Personendaten
    -0.75
     HasFactory
    -0.72
    MLLoader
    -0.61
     ſeveral
    -0.61
     antemano
    -0.59
     pleaſure
    -0.59
     économiques
    -0.58
     perfons
    -0.57
     Jefus
    -0.57
     quæ
    -0.56
    POSITIVE LOGITS
     Yu
    0.91
    Yu
    0.88
     Ye
    0.79
    Ye
    0.77
     yu
    0.68
     Ya
    0.61
     YU
    0.60
    IGraphics
    0.59
    Ya
    0.59
     ye
    0.59
    Activations Density 0.779%

    No Known Activations