© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11546
    Prev
    Next
    INDEX
    Explanations

    words related to novelty, features, testing, and technical analysis in different languages

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -0.79
    цездатний
    -0.75
     MainAxisSize
    -0.75
    principalTable
    -0.75
    ContentAsync
    -0.72
    ContentAlignment
    -0.72
     typelib
    -0.70
     ModelExpression
    -0.69
    TestingModule
    -0.69
     ―――――
    -0.68
    POSITIVE LOGITS
     "
    0.46
     k
    0.43
     K
    0.42
     “
    0.40
     (
    0.38
     R
    0.38
    WIRE
    0.37
    DataSnapshot
    0.37
    COUNTY
    0.37
     sev
    0.36
    Activations Density 4.516%

    No Known Activations