© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14954
    Prev
    Next
    INDEX
    Explanations

    words and phrases that mean "such as," technical words, and references

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    MigrationBuilder
    -0.85
    principalTable
    -0.72
    Lähteet
    -0.66
    mobileqq
    -0.64
    GOTREF
    -0.59
    AlterField
    -0.59
     poveznice
    -0.58
     sobremesa
    -0.58
     cref
    -0.57
    .}\
    -0.57
    POSITIVE LOGITS
    finanz
    0.56
     Anh
    0.54
    addContainerGap
    0.54
     Farmer
    0.53
     forskning
    0.53
    polizei
    0.53
    windowFixed
    0.52
    джу
    0.51
    Personensuche
    0.50
     vzor
    0.49
    Activations Density 2.396%

    No Known Activations