© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10786
    Prev
    Next
    INDEX
    Explanations

    lists of names, particularly Asian names

    oai_token-act-pair · gemini-2.0-flash

    Chinese names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     الحره
    -1.20
     betweenstory
    -1.14
     ModelExpression
    -1.06
    RegressionTest
    -1.05
    contentLoaded
    -1.05
     للاسماء
    -1.01
     nahilalakip
    -1.00
     estekak
    -1.00
     intptr
    -0.98
    migrationBuilder
    -0.98
    POSITIVE LOGITS
    di
    0.57
    min
    0.54
    he
    0.52
    men
    0.51
    si
    0.51
    lin
    0.47
    lu
    0.46
    le
    0.45
    zi
    0.45
    ji
    0.43
    Activations Density 1.288%

    No Known Activations